ARC-1
ARC-1 is an enterprise-ready MCP server that connects AI assistants to SAP ABAP systems via the ADT REST API, enabling AI-assisted SAP development with strong security defaults.
Read SAP Objects — Read ABAP source code (programs, classes, interfaces, function modules, includes, CDS views, BDEFs, service definitions/bindings, UI5/Fiori apps), DDIC objects (tables, domains, data elements, structures, views, message classes), BOR objects, revision history, and inactive/draft states. Supports active/inactive versions, method-level reads, and grep-based token-efficient search.
Search & Navigate — Search by object name (wildcards) or TADIR cross-package lookups, source code search, go-to-definition, find references/where-used, code completion, and class hierarchy lookup.
Write ABAP Objects — Create, update, or delete programs, classes, interfaces, function modules, CDS views, DDIC objects, and more. Supports surgical class edits (add/edit/delete methods, target specific class sections), RAP behavior pool skeleton generation, batch creation with activation, and automatic lock/unlock. Gated by explicit write enablement and package allowlists.
Activate Objects — Activate single or batch ABAP objects (with retry for S/4HANA quirks), publish/unpublish OData service bindings.
Diagnostics & Quality — Syntax check (with dry-run on supplied source), ABAP Unit tests, ATC code quality checks, CDS test case suggestions, compare active/inactive states, apply ADT quick fixes, inspect ABAP short dumps (ST22), profiler traces (hitlist, call tree, DB stats), SM02 system messages, and SAP Gateway error logs.
Lint & Formatting — Local abaplint with auto-fix (cloud/on-prem presets), server-side ADT PrettyPrinter formatting, and PrettyPrinter settings management.
Dependency & Impact Analysis — Compressed dependency context (public API contracts of all dependencies, 7–30x fewer tokens), CDS blast-radius impact analysis (upstream/downstream with RAP-aware classification), and reverse dependency lookup.
Transport Management — List, create, release, delete, and reassign CTS transport requests; check transport requirements; view object transport history; list transport layers and targets.
Git Operations (opt-in) — gCTS and abapGit support: list, clone, pull, push, commit, branch, and unlink repositories. Gated behind an explicit flag.
Data Access (opt-in) — Preview table contents and execute freestyle ABAP SQL queries, both gated by explicit environment variables.
System Management — Probe SAP system capabilities (HANA, RAP/CDS, BTP vs. on-prem, etc.), manage packages (create/delete/change), manage FLP catalogs/groups/tiles, and view object cache statistics.
Security & Authentication — Read-only by default; writes, data preview, free SQL, transport writes, and git writes each require explicit opt-in. Supports API key profiles, OIDC/JWT, OAuth 2.0, XSUAA, per-user SAP identity propagation, package allowlists, action deny lists, HTTP security headers, and multi-layer rate limiting.
Deployable as a Cloud Foundry app on SAP BTP with full platform integration including Destination Service, Cloud Connector, Principal Propagation, XSUAA OAuth proxy, and BTP Audit Log Service.
Available as a Docker image for containerized deployment, supporting various authentication methods and enterprise security configurations.
Connects AI assistants including GitHub Copilot to SAP systems via the ADT REST API, enabling AI-assisted SAP development with enterprise security controls and guardrails.
Supports OIDC/JWT authentication via Keycloak or any OpenID Connect provider for secure enterprise authentication to SAP systems.
Supports OIDC/JWT authentication via Entra ID, Keycloak, or any OpenID Connect provider for secure enterprise authentication to SAP systems.
Enterprise-ready MCP server for SAP ABAP systems connecting to SAP via the ADT REST API, providing 11 intent-based tools for reading/writing ABAP source, table data, CDS views, executing SQL, managing transports, and performing code analysis with enterprise security controls.
Uses SQLite for object caching in http-streamable deployments, enabling automatic source caching and dependency graph caching for improved performance.
ARC-1 — SAP ADT MCP Server
ARC-1 (pronounced arc one [ɑːrk wʌn]) — Enterprise-ready MCP server for SAP ABAP systems. Secure by default, deployable to BTP or on-premise, and hardened with large unit/integration/E2E test coverage.
ARC-1 connects AI assistants (Claude, GitHub Copilot, Copilot Studio, and any MCP client) to SAP systems via the ADT REST API. It ships as an npm package and Docker image.
Full Documentation | Quickstart | Tool Reference | ARC-1 Updates | Blog Series
📬 Stay current with ARC-1 — get major releases, upgrade and security notes, practical guides, and occasional questions where your feedback can shape what comes next. Join ARC-1 Updates →
📖 New: AI ABAP Development blog series — long-form posts on AI for ABAP, ARC-1 design, and real-world BTP / Copilot Studio / Joule walkthroughs. Read the series →
Why ARC-1?
Built for organizations that need AI-assisted SAP development with guardrails. Inspired by the pioneering work of abap-adt-api, mcp-abap-adt, and vibing-steampunk — ARC-1 adds what's needed to run in production:
Security & Admin Controls
Safe by default — read-only, no free SQL, no table preview, no transport writes, no Git writes. Enable each capability with explicit
SAP_ALLOW_*flagsAction deny list — block specific tool actions with
SAP_DENY_ACTIONS(for exampleSAPWrite.delete), without exposing low-level operation codes to adminsPackage restrictions — limit AI write operations (create, update, delete) to specific packages with wildcards (
--allowed-packages "Z*,$TMP"). Read operations are not restricted by package — use SAP's native authorization for read-level access controlData access control (off by default) —
SAPRead(type=TABLE_CONTENTS)andSAPQueryare gated behind explicit env vars (SAP_ALLOW_DATA_PREVIEW=true,SAP_ALLOW_FREE_SQL=true). These capabilities can expose application data or run ad-hoc SQL, so they are intentionally separated from the default development-tooling surface. They can be enabled for governed use cases, but should be reviewed against the SAP API Policy, your SAP agreement, and internal data-governance rulesExperimental data-source emergency brake — approved data/SQL deployments can set
SAP_BLOCKED_DATA_SOURCES=USR02,PA0002. ARC-1 then parses each SQL request and resolves active CDS plus replacement-object lineage before execution, denying direct or transitive exact-name matches and failing closed when lineage is unsupported or cannot be proven. The empty default adds no metadata calls. This denylist is defense in depth, not a production allowlist or replacement for SAP authorization/CDS DCL; see Authorization & Roles.Transport safety — transport reads are available for review, while transport mutations require both
--allow-writesand--allow-transport-writes. Update/delete operations auto-use the lock correction number when no explicit transport is providedGit workflow safety — Git operations are disabled by default. Enable explicitly with
--allow-git-writes/SAP_ALLOW_GIT_WRITES=trueAPI-key profiles — multi-key HTTP deployments can assign
viewer,viewer-data,viewer-sql,developer,developer-data,developer-sql, oradminper keyWrites restricted to
$TMPwhen enabled — only local/throwaway objects; writing to transportable packages requires explicit--allowed-packagesHTTP security headers (helmet) on by default — HSTS, CSP, X-Frame-Options, CORP, X-Content-Type-Options. COOP is deliberately not set so popup-based OAuth flows (Copilot Studio) keep working. No flag to disable.
Opt-in CORS for browser MCP clients —
ARC1_ALLOWED_ORIGINS(comma-separated, exact match). Off by default; native MCP clients don't need itLayered rate limiting — three layers out of the box: per-IP OAuth and shared MCP HTTP edge limits (Layer 1; MCP inherits the historical derived cap unless
ARC1_MCP_HTTP_RATE_LIMIToverrides it), per-user MCP quota (Layer 2, off by default — multi-user deployments opt in viaARC1_RATE_LIMIT=60), and a server-wide SAP-bound semaphore (Layer 3, default 10, on). HonorsRetry-Afteron 429/503 from SAP / BTP gateways. See the Rate Limiting GuideSupply-chain security — Dependabot (npm + GitHub Actions + Docker, weekly + same-day security advisories),
npm audit --audit-level=highPR gate, GitHub Dependency Review on every PR, CodeQL SAST, Trivy container scanning (scheduled multi-architecture HIGH/CRITICAL gate plus advisory release/dev scans), all third-party GitHub Actions pinned to commit SHA,SECURITY.mdpolicy with severity-tiered SLAs. Image and npm package both ship with provenance attestations, and the release workflow publishes a best-effort CycloneDX SBOM for the production npm dependency graph. See the security guide §13
Authentication
API key — simple Bearer token for internal deployments
OIDC / JWT — Entra ID, Keycloak, or any OpenID Connect provider
OAuth 2.0 — local browser-based login for BTP ABAP Environment service-key development
XSUAA — SAP BTP native auth with automatic token proxy for MCP clients
Per-user SAP identity — BTP Destination Service forwards the MCP user to SAP: Cloud Connector principal propagation for on-premise SAP, or
OAuth2UserTokenExchangefor BTP ABAP Environment
BTP Cloud Foundry Deployment
Deploy ARC-1 as a Cloud Foundry app on SAP BTP with full platform integration:
Destination Service — connect to SAP systems via managed destinations
Experimental multi-target mode — the default-off, mutation-free BTP mode discovers destinations marked
arc1.enabled=trueand exposes pinned SID/client plus aggregate endpoints (setup, administration)Cloud Connector — reach on-premise systems through the connectivity proxy
Per-user destinations — user identity forwarded end-to-end via X.509 certificates for on-premise SAP, or exchanged for an ABAP bearer token for BTP ABAP Environment
XSUAA OAuth proxy — MCP clients authenticate via standard OAuth, ARC-1 handles the BTP token exchange
Audit logging — structured events to stderr, file, or BTP Audit Log Service
Token Efficiency
12 intent-based tools instead of 200+ individual tools — keeps tool selection simple, with the schema payload guarded by CI budgets and a hyperfocused 1-tool mode for tight context windows
Method-level read/edit — read or update a single class method, not the whole source (up to 20x fewer tokens)
Focused source and dependency context — use targeted
SAPReadfor exact implementation behavior. For business purpose, reviews or test design, start withSAPContext(action="deps", type=..., name=...)for available Knowledge Transfer Documents (SKTD/KTD) and dependency contracts, then compare requirements with source. Without documented requirements, intent is unverified.
Built-in Object Caching
Server-validated source caching — every SAP object read is cached in memory (stdio) or SQLite (http-streamable). Repeated reads use
If-None-Match/ETag conditional GET, so unchanged objects return from cache after SAP confirms304 Not Modified.Dependency parsing reuse — unchanged, authorized source can reuse parsed dependencies and contracts in memory. Aggregate dependency graphs are not cached; SAP authorization and source validation still apply.
KTD-aware context — Knowledge Transfer Documents use the source cache and are revalidated when composed into
SAPContext(action="deps").Live where-used —
SAPContext(action="usages")and CDS impact analysis query SAP's current repository index with the caller's identity; no startup repository scan is required.Active/inactive source views —
SAPReadacceptsversion="active" | "inactive" | "auto"and warns when the active source has an unactivated draft.Write invalidation — when
SAPWriteorSAPActivatemutates an object, both active and inactive source cache entries are dropped; next read revalidates or fetches fresh source.
See docs/caching.md for full documentation.
Testing
3,474 unit tests (
104unit test files, mocked HTTP)262-test default integration profile against live SAP systems, with explicit skip reasons when credentials or fixtures are missing
141-test default E2E profile that executes real MCP tool calls against a running ARC-1 server and live SAP system
Manual slow SAP profiles keep broad where-used, RAP full-stack, and recursive CTS release coverage out of the PR path (
test:integration:slow,test:e2e:slow, GitHub SAP Slow Tests workflow)CRUD lifecycle and BTP smoke lanes included (
test:integration:crud,test:integration:btp:smoke)CI matrix on Node
22and24; live SAP integration + E2E run on internal PRs and manual dispatch, with SAP jobs gated off for docs/chore PRs and external forksReliability telemetry + coverage published as informational CI signals (non-blocking)
Tools Refined for Real-World Usage
The 12 tools are designed from real LLM interaction feedback:
Tool | What it does |
SAPRead | Read exact ABAP source, method bodies, grep matches, table data, CDS views, access controls ( |
SAPSearch | Object search + full-text source code search across the system |
SAPWrite | Create/update/delete ABAP source and DDIC metadata with automatic lock/unlock (PROG, CLAS, INTF, FUNC, FUGR, INCL, DDLS, DCLS, DDLX, BDEF, SRVD, SRVB, SKTD/KTD, TABL, DOMA, DTEL, MSAG; availability adapts for BTP). Class updates can target local includes ( |
SAPActivate | Activate ABAP objects — single or batch (essential for RAP stacks), with guarded retry for the S/4HANA ED064 batch quirk. Publish/unpublish OData service bindings (SRVB) |
SAPNavigate | Go-to-definition, find references, code completion |
SAPQuery | Execute ABAP SQL with table-not-found suggestions and automatic chunking for simple long literal |
SAPTransport | CTS transport management (list/get/create/release/delete/reassign/release-recursive), transport layer/target lookup, package transport requirement checks, and reverse lookup history ( |
SAPGit | Git-based ABAP workflows across gCTS and abapGit (list/clone/pull/push/commit/branch/unlink) with backend auto-selection and safety gating ( |
SAPContext | Dependency APIs ( |
SAPLint | Local ABAP lint (system/release-aware presets, auto-fix, pre-write validation) + ADT PrettyPrint (server-side formatting) |
SAPDiagnose | Syntax check, ABAP Unit tests, ATC code quality, CDS test-case suggestions, active/inactive object-state comparison, generic ADT quickfix proposals/application deltas, gateway/system message diagnostics, short dumps, profiler traces, and the on-prem authorization trace ( |
SAPManage | Feature probing, cache statistics, package lifecycle/change-package operations, and FLP catalog/group/tile helpers |
Tool definitions automatically adapt to the target system (BTP vs on-premise), removing unavailable types and adjusting descriptions so the LLM never attempts unsupported operations.
Feature Detection
ARC-1 probes the SAP system at startup and adapts its behavior:
Detects HANA, gCTS, abapGit, RAP/CDS, AMDP, UI5, and transport availability
Auto-detects BTP vs on-premise systems
Maps SAP_BASIS release to the correct ABAP language version
Each feature can be forced on/off or left on auto-detect
In shared-credential mode (technical user), runs a startup auth preflight once and blocks SAP tool calls with a clear error on 401/403 to avoid repeated failed logins and potential user lockout
Related MCP server: mcp-server-wazuh
ADT API Status and Strategy
ARC-1 is a governed development-tooling proxy around ADT behavior — code checks, build/activate, transport management, AI-assisted ABAP authoring, Git workflows — not a bulk data-extraction product. It runs with real user identity, respects SAP authorization, and keeps audit and rate controls in place.
Where this stands under SAP's API Policy is covered in full in SAP API Policy & Architecture Alignment — what API Policy v.4.2026a says clause by clause, why the ADT question is more nuanced than "undocumented API", where ARC-1 sits against SAP's reference architecture for third-party MCP access, and the specific questions to put to your SAP contact. Short version: usable at your own risk, and worth asking SAP before production.
Two ARC-1 capabilities can expose business data or execute ad-hoc SQL. Both are off by default and require explicit opt-in env vars, so the operator makes a deliberate decision before they are reachable:
Capability | Env var | Default | Policy note |
Named table content preview ( |
|
| Can expose application-table data; keep off unless the use case is approved. |
Freestyle ABAP SQL ( |
|
| Executes ad-hoc ABAP SQL; keep off unless the use case is approved. |
Exact source blocklist (experimental) |
| empty (off) | Denies exact direct/transitive table or CDS dependencies; active mode is deliberately fail-closed and slower. |
When either capability is enabled, successful data-preview bodies are limited cumulatively per tool
call (2 MiB by default), and only two data-result calls per process remain admitted through parsing
and serialization. SAPQuery.maxRows is separately clamped to 10,000, but wide rows can reach the
byte limit much earlier. See Configuration before tuning
ARC1_MAX_DATAPREVIEW_RESPONSE_BYTES or ARC1_MAX_CONCURRENT_DATA_RESULTS.
With both flags at their defaults, ARC-1's data/sql rows are unreachable. Turning either flag on is a valid operational choice for approved scenarios, but it should be deliberate: check the current SAP API Policy, the customer's SAP agreement, SAP authorizations, and internal data-protection rules before enabling it on a productive system.
ARC-1's strategy is to stay close to documented and discoverable ADT behavior, probe system capabilities before exposing tools, keep conservative security defaults (writes off, data preview off, free SQL off, package allowlist $TMP), and continuously review SAP's guidance as it evolves. This README is not a compliance decision for any specific customer landscape, but the default posture is intended to support normal governed development use rather than block it.
Versioning & Stability
From 1.0 onward ARC-1 follows semantic versioning: patch releases fix bugs, minor releases add backward-compatible capability, and breaking changes to the MCP tool surface, configuration, or auth contract bump the major version.
Experimental, default-off features are excluded from this guarantee until they are promoted — they are clearly labeled and their surface may still change in a minor release. Today this covers the multi-target BTP mode (ADR-0006 / ADR-0007) and the data-source blocklist.
What changed per release: the annotated Release Notes give each release its impact and upgrade action; CHANGELOG.md lists every merged PR.
Quick Start
Install as an Agent Plugin — one portable install for the MCP server and all bundled SAP skills in GitHub Copilot, VS Code, Cursor, Codex, and other compatible clients:
copilot plugin marketplace add arc-mcp/arc-1
copilot plugin install arc-1@arc-1Agent Plugins 1.0 does not define secret prompts, so create the ARC-1 .env in the installed
plugin's persistent data directory before connecting to SAP. See the
Agent Plugin guide for client-specific installation,
safe configuration, and verification.
Install in Claude — pick your surface (full guide: Install in Claude):
Claude Desktop — download the latest
arc-1-*.mcpbfrom Releases and double-click it (or Settings → Extensions). Claude prompts for your SAP connection. (The.mcpbis attached to releases automatically; if the newest one doesn't have it yet, see Install in Claude.)Claude Code — one install for the MCP server and all SAP skills:
/plugin marketplace add arc-mcp/arc-1 /plugin install arc-1@arc-1Any MCP client / manual — run it directly:
npx arc-1@latest --url https://your-sap-host:44300 --user YOUR_USERTrying it out on your laptop? → Quickstart
Full local dev setup (Docker, cookie extractor, client configs)? → Local Development
Deploying for a team / BTP? → Deployment
Blog Series — AI ABAP Development
A long-form series on blog.zeis.de covering AI for ABAP development, ARC-1's design, and real-world walkthroughs:
Introducing ARC-1: A Secure ADT MCP Server for Enterprise SAP Development
ARC-1 on SAP BTP: Secure ABAP Agentic Development Beyond the Laptop
ARC-1 with Copilot Studio: SAP System Context Beyond Developers
ARC-1 with Joule Studio: Bringing Real ABAP System Context into Joule
Full list and new posts → blog.zeis.de/tags/ai-abap-development-series.
Documentation
Full documentation is available at docs.arc-1-mcp.com.
Guide | Description |
5-minute npx + Claude Desktop setup | |
Portable server + all skills for Copilot, VS Code, Cursor, Codex, and compatible clients | |
Desktop | |
Full local dev — all install methods, MCP client configs, SSO cookie extractor | |
Multi-user deployment — Docker, BTP Cloud Foundry, BTP ABAP | |
Choose the BTP topology and follow the correct deployment, auth, destination, and operations guides | |
MTA deployment, topology decision, role handoffs, and safe acceptance | |
Changes, roles, secrets, scaling, upgrades, rollback, and customer handover | |
Experimental read-only BTP multi-target deployment, destinations, roles, and client configuration | |
Every flag and env var, one table | |
Update procedures per install method | |
Layer A / Layer B auth internals, coexistence matrix | |
Complete reference for all 12 tools | |
Add your own | |
System architecture with diagrams | |
Agent workflow patterns and best practices | |
Reusable ARC-1 agent skills, including GitHub Copilot in Eclipse and VS Code ADT setup | |
Long-form posts on AI for ABAP development, ARC-1 internals, and real-world walkthroughs |
Development
npm ci && npm run build && npm testSee CLAUDE.md for codebase structure, testing commands, and contribution guidelines.
Credits
Project | Author | Contribution |
oisee | Original Go MCP server — ARC-1's starting point | |
Marcello Urbani | TypeScript ADT library, definitive API reference | |
Mario Andreschak | First MCP server for ABAP ADT | |
Lars Hvam | ABAP parser/linter (used via @abaplint/core) |
License
MIT
Available Tools
8 toolsSAPContextARead-only
Primary tool for understanding ABAP/CDS objects before specs, reviews, explanations, or changes — use instead of SAPRead when the user asks what an object does. Returns intent first (the object KTD when available) then compressed dependency contracts. Use SAPRead after SAPContext for exact source/method bodies/grep/drafts.
Decision rule — pick the action from the user's question:
"What breaks if I change ?" / "Who consumes <I_*>?" / "Blast radius" → action="impact" (DDLS only).
"Which includes/appends extend ?" → action="structure", type="TABL".
"What does do?" / "Explain" / "deps before editing" → action="deps" (default); type+name required.
"Find all callers of " → action="usages" (live SAP where-used lookup).
impact (CDS blast-radius): upstream AST deps + downstream where-used, classified into RAP buckets (projectionViews, bdefs, serviceDefinitions, serviceBindings, accessControls, metadataExtensions, abapConsumers, documentation, tables, other) + sibling-consistency hints. Use this instead of text-scanning DDDDLSRC/ACMDCLSRC with SAPQuery (it filters the noise). Optional includeIndirect, siblingCheck, siblingMaxCandidates. deps: target KTD when available + selected dependency contracts, derived from source (not SAP-native relationships or a complete inventory). Counts distinguish root candidates from recursive attempts. Standard helper names are filtered. For CDS, includes dependency DDL/field catalogs for cl_cds_test_environment. structure (TABL only): the DDIC include/append tree.
Non-CDS reverse-lookup: SAPNavigate(references); CDS: impact. Full detail: docs_page SAPContext.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Object name (e.g., ZCL_ORDER) | |
| type | No | Root type. deps requires type+name, even with source. Optional for action="impact" (defaults to DDLS) or usages (unique name lookup); structure requires TABL. | |
| depth | No | Dependency depth: 1 = direct deps only (default), 2 = deps of deps, 3 = maximum. Higher depth = more context but more SAP calls. | |
| group | No | Required for FUNC type. The function group containing the function module. | |
| action | No | Action: "impact" = CDS blast-radius analysis (DDLS only). USE THIS for any question like "what breaks if I change <view>", "who consumes <I_*>", "impact analysis on <CDS>", "downstream of <view>". Returns upstream AST dependencies + downstream where-used classified into RAP buckets (projectionViews, bdefs, serviceDefinitions, serviceBindings, accessControls, metadataExtensions, abapConsumers, documentation, tables, other), plus additive sibling-consistency diagnostics (consistencyHints + siblingExtensionAnalysis) when related DDLS siblings show asymmetric DDLX coverage. ALWAYS prefer over SAPQuery against DDDDLSRC/ACMDCLSRC/DDLXSRC_SRC/SRVDSRC_SRC (those text-scans produce noise this classifier filters out). Non-DDLS input returns a guardrail error. "deps" (default) = source-derived dependency contracts plus KTD when available. Requires type+name, even with source. Not a complete inventory; read source for behavior. "usages" = live SAP where-used lookup. Provide "type" when known; without it, the name must resolve uniquely. Prefer "impact" for CDS. "structure" = TABL includes/appends. | |
| source | No | Optional: provide source directly instead of fetching from SAP. Saves one round-trip if you already have the source from SAPRead. | |
| maxDeps | No | Max dependencies to resolve (default 20). Lower = faster + fewer tokens. | |
| includeKtd | No | deps: When true/default, prepend the object Knowledge Transfer Document (KTD/SKTD) when one exists. Set false to skip the KTD lookup. | |
| maxResults | No | usages: max entries (default 100); impact: max per downstream bucket (default 50). Max 1000. "usageCount"/"summary" stay true totals, not page sizes. | |
| siblingCheck | No | impact: Enable sibling metadata-extension consistency analysis. Default true. | |
| includeIndirect | No | impact: Include indirect (transitive) downstream where-used entries. Default false. | |
| siblingMaxCandidates | No | impact: Maximum sibling DDLS candidates to compare. Default 4; hard cap 10. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint annotation, the description discloses that dependencies are 'derived from source (not SAP-native relationships or a complete inventory)', notes that 'Standard helper names are filtered', warns of a 'guardrail error' for non-DDLS impact input, and explains that higher depth costs more SAP calls. This level of behavioral detail far exceeds what the annotation provides.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with a clear opening purpose, a decision-rule table, and per-action details, front-loading the most important guidance. It is long, but that length is justified by the tool's complexity (12 parameters, 4 actions). It loses a point because some information is redundant with the action parameter description, which could be trimmed.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex tool without an output schema, the description compensates thoroughly: it explains the conceptual return content per action (KTD, RAP buckets, dependency contracts, includes/appends), outlines limitations, names alternative tool routes, and covers parameter usage contexts. This is complete enough for an agent to decide and invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides 100% parameter description coverage, including detailed constraints, enums, and defaults for all 12 parameters (e.g., action's full explanation, structure's TABL requirement). The tool description largely recaps this information rather than adding new semantic insight, so the baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific purpose ('Primary tool for understanding ABAP/CDS objects') with a clear verb and resource, and explicitly distinguishes itself from sibling SAPRead ('use instead of SAPRead when the user asks what an object does'). It also summarizes the output format ('Returns intent first ... then compressed dependency contracts'), leaving no ambiguity about the tool's function.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit when-to-use and when-not-to-use guidance: it directs users to SAPRead for exact source/method bodies, to SAPNavigate for non-CDS reverse-lookup, and states a preference over SAPQuery for CDS text-scans ('ALWAYS prefer over SAPQuery'). It even offers a decision rule mapping user questions to specific actions, which is exemplary routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
SAPDiagnoseA
ABAP diagnostics and runtime analysis. Actions:
"syntax": syntax-check (name+type; optional version; optional source = pre-write dry-run, nothing written).
"unittest": harmless ABAP Unit for CLAS/PROG/FUGR or DEVC (exact; includeSubpackages recurses).
"unittest_ci": harmless package tests with source reconciliation; empty/incomplete runs fail.
"atc": run ATC checks (name+type or objects [{type,name}], max 20; omit variant to bind the system default; unknown variant = error). "atc_variants": list variants + that default (variant = name filter; read-only).
"atc_ci": package ATC CI; requires available API and verified selection.
"cds_testcases": SAP-suggested ABAP Unit test cases for a CDS entity (name; read-only; SAP_BASIS 8.16+).
"object_state": compare active vs inactive source versions (name+type; CLAS compares all includes). Returns ETags/hashes/divergence flags.
"quickfix": proposals at name+type+source+line (optional column/sourceUri).
"apply_quickfix": return proposal text deltas without writing; needs quickfix inputs + proposalUri/proposalUserContent.
"dumps": list/read ST22 short dumps (no id = list; id = read; includeFullText, sections).
"traces": list profiler traces; id+analysis analyzes one.
"trace_start": arm a profiler trace for the NEXT matching execution, then reproduce and read via "traces" (write scope; defaults: next HTTP request, SQL on).
"trace_requests": list armed trace requests. "trace_cancel": cancel one by id (write scope).
"system_messages": list SM02 messages. "gateway_errors": list /IWFND/ERROR_LOG (on-prem; detailUrl or id+errorType for detail).
"odata_perf": diagnose why an OData call is slow (url = host-relative path); returns the sap-statistics timing split (DB/ABAP/framework/auth). Read-only; needs allowDataPreview.
"authorization_trace": read the on-prem STUSERTRACE auth trace (SUAUTHVALTRC); needs SAP_ALLOW_DATA_PREVIEW.
"cds_sql": show the native SQL a CDS view compiles to (name; read-only).
"sql_trace_state" / "set_sql_trace_state" (sqlOn; needs SAP_ALLOW_WRITES) / "sql_trace_directory": ST05 SQL-trace control. Quickfix workflow: syntax/ATC → quickfix → apply_quickfix → write via SAPWrite. Full action reference: docs_page SAPDiagnose.
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | Dump or trace ID (for dumps/traces actions); also the trace-request id to cancel (for trace_cancel). Omit to list, provide to get details. | |
| to | No | system_messages/gateway_errors upper time bound. | |
| url | No | odata_perf: host-relative OData path from the app network request (e.g. /sap/opu/odata4/sap/.../Entity?$filter=…). Absolute URLs rejected. | |
| from | No | system_messages/gateway_errors lower time bound. | |
| line | No | Required quickfix/apply_quickfix source line. | |
| name | No | syntax/unittest/atc/object_state object name; cds_testcases/cds_sql CDS entity or DDLS name. | |
| type | No | Object type; unittest accepts CLAS, PROG, FUGR, or DEVC. | |
| user | No | SAP-user filter for dumps, feeds, or authorization_trace. | |
| sqlOn | No | set_sql_trace_state: true arms ST05 SQL trace, false disarms; user filters the SAP user. | |
| action | Yes | ||
| column | No | Quickfix source column (default 0). | |
| source | No | Current source code (required for quickfix/apply_quickfix). | |
| objects | No | ATC only, instead of name/type/url. One batch + at most one verification. Returns coverage; unreported objects stay incomplete. No packages. | |
| variant | No | atc/atc_ci variant; atc_variants name filter (*=all) | |
| version | No | syntax source version (default active); inactive checks pending changes. | |
| analysis | No | traces with id: hitlist=hot spots, statements=call tree, dbAccesses=DB access stats. | |
| coverage | No | unittest only: collect statement/branch/procedure coverage and methodsBelowFull. Unavailable measurements do not discard test results. Default false. | |
| packages | No | CI exact packages; 1–50 total with packageTrees. | |
| sections | No | dumps detail chapter IDs, e.g. ["kap0","kap3","kap8"]; omit for focused defaults. | |
| sqlTrace | No | trace_start SQL capture (default true; required for analysis="dbAccesses"). | |
| aggregate | No | trace_start aggregation (default true). | |
| detailUrl | No | Detail path: canonical /sap/bc/adt/gw/errorlog/...; no absolute URLs. | |
| errorType | No | gateway_errors: required with id instead of detailUrl, e.g. "Frontend Error". | |
| sourceUri | No | quickfix/apply_quickfix source URI; default type/name main source. Set for includes, e.g. /includes/definitions. | |
| traceUser | No | trace_start/trace_requests SAP user (default connected user). | |
| authObject | No | Authorization object filter, e.g. S_TCODE. | |
| maxResults | No | Result limit: dumps/system_messages/gateway_errors default 50; authorization_trace 100. Capped. | |
| objectType | No | trace_start match type; defaults: http→url, dialog→transaction, batch→report, rfc→functionModule. | |
| description | No | trace_start label. | |
| processType | No | trace_start work process (default http/OData): dialog=SAP GUI, batch=background job, rfc=RFC. | |
| proposalUri | No | Quickfix proposal URI from quickfix action (required for apply_quickfix). | |
| expiresHours | No | trace_start expiry in hours (default 24). | |
| onlyFailures | No | authorization_trace: only denied checks (RC<>0), like SU53. | |
| packageTrees | No | CI packages including subpackages. | |
| resultFormat | No | unittest: legacy|structured|junit; atc: legacy|structured; other actions reject it. | |
| configuration | No | atc_ci: optional configuration. | |
| maxExecutions | No | trace_start executions to capture (default 1). | |
| failOnSeverity | No | atc_ci failure threshold (default error). | |
| timeoutSeconds | No | Timeout 1–3600s: unittest/atc default 300; CI overall default 600. | |
| includeFullText | No | dumps detail: include full formattedText (default false). | |
| includeReportXml | No | CI XML reports (default false; 256 KiB total cap). | |
| includeSubpackages | No | ||
| proposalUserContent | No | Opaque userContent from quickfix action (required for apply_quickfix). May be an empty string; pass through exactly. | |
| proposalAffectedObjects | No | quickfix affectedObjects; provide current content for each source unit when applying multi-object fixes. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description goes far beyond the annotations: it marks syntax as a dry-run that writes nothing, labels ABAP Unit runs as harmless, discloses write scope for trace_start and set_sql_trace_state, and notes limits like max 20 objects and 256 KiB CI XML cap. It also exposes behaviors such as source reconciliation and pass-through requirements for proposalUserContent. No contradiction with the readOnlyHint=false/destructiveHint=false annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long, but justified by 23 distinct actions. It is structured with quoted action names and terse clauses, front-loads the overall purpose, and includes a workflow summary plus a pointer to a full reference. Some parameter details duplicate the schema, but the action list format makes it scannable and useful for selection.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex 44-parameter, 23-action tool with no output schema, the description covers prerequisites, constraints, defaults, and sequencing well. It explains return concepts for some actions (ETags/hashes, timing split, coverage) but not all, and the external docs_page reference fills remaining gaps. This is strong but not exhaustive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 95%, so the baseline is 3, but the description adds meaningful action-level semantics: id can mean list or detail, variant binds the system default, objects have batch/verification constraints, and resultFormat is rejected by non-test actions. This supplements the already-strong schema descriptions rather than merely repeating them.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a clear domain statement, 'ABAP diagnostics and runtime analysis', then enumerates every action with a concise verb phrase. It distinguishes this tool from siblings like SAPRead, SAPLint, and SAPManage by focusing on diagnostics, analysis, tracing, and checks rather than generic read/write operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Each action is tagged with usage-relevant context: read-only vs write scope, required permissions (SAP_ALLOW_WRITES, allowDataPreview), platform constraints (on-prem), and failure semantics (unknown variant = error, empty/incomplete runs fail). The explicit Quickfix workflow shows sequencing. It does not explicitly compare against sibling tools, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
SAPLintA
Run local abaplint rules on ABAP/CDS source (auto-selects cloud or on-prem rules by system type). Actions:
"lint": check source (errors+warnings) for ABAP (PROG/CLAS/INTF/FUNC) and CDS (DDLS).
"lint_and_fix": lint + auto-fix fixable issues (keyword case, obsolete statements); returns fixed source.
"list_rules": list rules + current config (no source).
"format": pretty-print via SAP's ADT formatter (needs source).
"get_formatter_settings" / "set_formatter_settings": read/update the system's global PrettyPrinter (indentation bool, style keywordUpper|keywordLower|keywordAuto|none; set is blocked read-only). lint/lint_and_fix/list_rules run locally; format/*_formatter_settings call SAP. For ATC/syntax/unit tests use SAPDiagnose.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Object name (used for filename detection) | |
| rules | No | Rule overrides: { "rule_name": false } to disable, { "rule_name": { "severity": "Warning" } } to configure. Overrides system defaults. | |
| style | No | PrettyPrinter: keyword casing (for set_formatter_settings) | |
| action | Yes | Check type | |
| source | No | ABAP or CDS source code to lint/format (not needed for list_rules/get_formatter_settings) | |
| indentation | No | PrettyPrinter: indent source (for set_formatter_settings) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds significant context beyond annotations: it discloses which sub-actions are local vs. remote (calling SAP), that the 'set' for formatter settings is 'blocked read-only', and that lint_and_fix auto-fixes issues and returns fixed source. Annotations provide readOnlyHint=false and destructiveHint=false, but the description adds richer behavioral detail about the mixed local/remote execution model and the blocked set operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and front-loads the core purpose in the first sentence before enumerating actions. The bullet list is scannable. Slight length from the detail on actions and their parameters, but each sentence earns its place and covers genuinely useful information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description carries the burden of explaining what each action returns, which it does (fixed source for lint_and_fix, rules+config for list_rules). It covers the required parameter (action), the six actions thoroughly, and relevant tool boundaries. Minor gap: it doesn't specify the return shape of the lint/format actions beyond lint_and_fix, but the overall coverage is strong.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description adds value by mapping which actions require which parameters (e.g., 'source needed for format', 'not needed for list_rules/get_formatter_settings', style/indentation are 'for set_formatter_settings'). This goes beyond the bare schema descriptions and clarifies parameter-to-action relationships.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Run local abaplint rules on ABAP/CDS source' with a specific verb (run), resource (ABAP/CDS source), and explicit action categories for each sub-command. It distinguishes itself from siblings by explicitly noting 'For ATC/syntax/unit tests use SAPDiagnose'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains both when to use each action (lint, lint_and_fix, list_rules, format, formatter settings) and what each does. It explicitly calls out that lint/lint_and_fix/list_rules run locally while format and formatter settings call SAP, and names the alternative tool SAPDiagnose for ATC/syntax/unit tests. This is exceptional guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
SAPManageADestructive
Probe and report SAP system capabilities. Use BEFORE operations that depend on optional features (abapGit, RAP/CDS, AMDP, HANA, UI5/Fiori, CTS transports, FLP). Also handles package (DEVC) lifecycle.
Actions:
"features": cached feature status (fast, no round-trip; id, available, mode, probedAt). "probe": re-probe now (feature probes + auth + discovery refresh). "cache_stats": object cache health.
"create_package" / "delete_package" / "change_package": DEVC lifecycle via ADT packages API.
FLP read: flp_list_catalogs, flp_list_groups, flp_list_tiles (catalogId). FLP write: flp_create_catalog, flp_create_group, flp_create_tile, flp_add_tile_to_group, flp_delete_catalog. Classic designer tile/target-mapping model, deprecated since S/4HANA 2023; Work Zone exposure v2 needs LADIs (SAPRead type=UIAD).
"set_api_state": release/revoke an object's API release contract (objectUri, or name+objectType; apiState defaults RELEASED, contract defaults C1 — C0 for SRVD, C3 for classic views). Write counterpart of SAPRead(type="API_STATE").
Returns features + systemType ("onprem"/"btp"); "available: false" means do NOT attempt dependent operations.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Package name (required for create_package and delete_package). | |
| tile | No | Tile definition for flp_create_tile. | |
| title | No | Title — required for flp_create_catalog and flp_create_group. | |
| action | Yes | Action to execute. Read actions: features, probe, cache_stats, flp_list_catalogs, flp_list_groups, flp_list_tiles. Mutating package/FLP actions require writable safety config and write scope in authenticated mode. | |
| groupId | No | FLP group/page identifier (required for flp_create_group, flp_add_tile_to_group). | |
| apiState | No | For set_api_state: target state of the object's API release contract — RELEASED (mark released for ABAP Cloud / Clean Core) or NOT_RELEASED (revoke). Default RELEASED. Visibility (ABAP Cloud / Key User Apps) follows the contract's defaults. Read the current state first with SAPRead(type="API_STATE"). | |
| contract | No | For set_api_state: which release contract to set. Default C1 (Key-User/Cloud — the common clean-core contract). Object types support different contracts: e.g. service definitions (SRVD) only support C0, classic DDIC views only C3, behavior definitions and tables support C0+C1. If the object does not support the chosen contract, the error lists the ones it does. | |
| domainId | No | Domain ID — required for flp_create_catalog (e.g., ZARC1_SALES). | |
| catalogId | No | FLP catalog identifier — accepts either full ID (X-SAP-UI2-CATALOGPAGE:MY_CAT) or domain ID (MY_CAT). Required for flp_list_tiles, flp_create_tile, flp_add_tile_to_group, flp_delete_catalog. | |
| objectUri | No | ADT URI of the object to move (e.g., /sap/bc/adt/oo/classes/zcl_my_class). If not provided, resolved automatically from objectName + objectType via search. For set_api_state: the object whose API release contract to set (or pass name + objectType instead). | |
| transport | No | Optional transport request (corrNr) for create_package, delete_package, or change_package. | |
| newPackage | No | Target package to move the object to. Required for change_package. | |
| objectName | No | Object name to move (e.g., ZCL_MY_CLASS). Required for change_package. | |
| objectType | No | ADT object type (e.g., CLAS/OC, DDLS/DF, PROG/P). Required for change_package. For set_api_state: object type of "name" when objectUri is omitted (e.g. CLAS, INTF, DDLS, TABL). | |
| oldPackage | No | Current package of the object. Required for change_package. | |
| description | No | Package description (required for create_package). | |
| packageType | No | Package type for create_package (default: development). | |
| responsible | No | Person-responsible: an existing ABAP user (XUBNAME, max 12 chars); an email is rejected. Defaults to the connection user; pass explicitly under principal propagation. BTP: auto-resolved from prior creates. | |
| superPackage | No | Parent package for create_package (defaults to empty root package). | |
| recordChanges | No | Whether the created package records object changes in transport requests. Defaults to true for non-LOCAL software components or when a transport layer is set; false for literal LOCAL packages. | |
| tileInstanceId | No | Tile instance ID in the source catalog (required for flp_add_tile_to_group). | |
| transportLayer | No | Transport layer for create_package (optional; required by some transportable landscapes). | |
| softwareComponent | No | Software component for create_package (default: LOCAL on-prem, ZLOCAL on BTP). |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare destructiveHint=true and readOnlyHint=false, and the description aligns: it distinguishes read actions ('features', 'probe', 'cache_stats', flp_list_*) from mutating actions and notes that mutating ones 'require writable safety config and write scope in authenticated mode'. The description adds meaningful behavioral context beyond annotations: caching semantics ('fast, no round-trip'), returns (features + systemType), and the concrete directive that 'available: false means do NOT attempt dependent operations'. Slight deduction for not spelling out exactly what 'probe' validation entails in terms of side effects or cleanup.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but front-loaded with the most important purpose and usage guidance. The action list is well-structured with a clear read vs write grouping, and FLP methods are compactly enumerated. Minor deduction: the action enumeration overlaps heavily with the schema's action enum, and the set_api_state detail sentence is somewhat bulky, but overall every section earns its place and the prose is resource-efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
This is a high-complexity tool (23 params, multiple sub-domains: probe/features, package lifecycle, FLP read and write, set_api_state). The description covers every domain, rules out ambiguities (deprecation, alternative LADI path), documents defaults and edge cases (contract support per object type), and states return values (features + systemType) since there's no output schema. Given the breadth and the strong schema coverage, the description is appropriately complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all 23 parameters thoroughly with inline descriptions. The description adds a handful of meaningful semantics beyond the schema: the action list with read-vs-mutating classification, the set_api_state default values (RELEASED, C1, with C0 for SRVD and C3 for views) which clarify the apiState/contract params, and the write-scope gating requirement. However, most parameter semantics live in the schema, so the description doesn't carry the heavy lifting here — hence a baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb+resource statement: 'Probe and report SAP system capabilities' and explicitly frames when to use it ('Use BEFORE operations that depend on optional features'). It clearly distinguishes from siblings by listing covered domains (abapGit, RAP/CDS, AMDP, HANA, UI5/Fiori, CTS transports, FLP) and package lifecycle. The action list with inline sub-descriptions clearly delineates the tool's many functions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit usage context: 'Use BEFORE operations that depend on optional features' and lists specific features. It also gives exclusion guidance, e.g., 'Classic designer tile/target-mapping model, deprecated since S/4HANA 2023; Work Zone exposure v2 needs LADIs (SAPRead type=UIAD)' — directing to an alternative tool. The 'available: false means do NOT attempt dependent operations' instruction is a clear when-not-to-proceed signal.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
SAPReadARead-only
Read SAP ABAP source or metadata. For purpose, explanations, specs, reviews or pre-change context, prefer SAPContext first. DDIC metadata: omit format (default text); structured is CLAS-only for ordinary reads. Types: PROG, CLAS, INTF, FUNC, FUGR (expand_includes=true for all include sources), INCL, DDLS, DCLS, DDLX, BDEF, SRVD, SRVB, SKTD/KTD (KTD aliases SKTD), TABL (covers both transparent tables AND DDIC structures — no separate STRU type), TTYP, VIEW, DOMA, DTEL, TRAN, TABLE_CONTENTS (single-column filter), TABLE_QUERY (multi-column WHERE via the freestyle endpoint; gated by allowDataPreview; CDS views need SAP_BASIS 752+), DEVC, SOBJ (BOR — method param reads one method), SYSTEM, COMPONENTS, MSAG, TEXT_ELEMENTS, VARIANTS, BSP, BSP_DEPLOY, API_STATE (contract states C0-C4; objectType for non-class), INACTIVE_OBJECTS (no name; pending-activation list), AUTH, FEATURE_TOGGLE, ENHO, VERSIONS, VERSION_SOURCE. AUTH/FEATURE_TOGGLE/ENHO/VERSIONS/VERSION_SOURCE are on-prem only. CLAS: method="*" for signatures, method="NAME" for one body, or grep. Global class declaration/implementation: MAIN (omit include). definitions/implementations contain local helpers. Details: docs_page SAPRead. grep: case-insensitive regex; returns matching lines, context and line numbers, with owning class/method for CLAS. Optional version parameter: source types default active; "inactive" requests the draft (SAP may return active if none); "auto" uses the developer view. DTEL omitted/auto uses its developer view; explicit values pass through. Active source reads note when a draft exists.
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | action="diff" NEW side (default "inactive" = pending unactivated changes). Same values as from. | |
| from | No | action="diff" OLD side: "active" (default), "inactive", a revision id from SAPRead(type="VERSIONS"), or a /sap/bc/adt/ revision URI. | |
| grep | No | Regex pattern (case-insensitive) to search within the object source. Returns only matching lines with 1-based line numbers and ±3 context lines, instead of the full source — token-efficient. For CLAS, matches are annotated with the owning class/method; combine with include= to scope a section, but do NOT combine with method= (use grep to find, then method= to read). Works for source-bearing types (CLAS, INTF, DDLS, DCLS, BDEF, SRVD, SRVB, SKTD/KTD, DDLX, TABL, PROG, FUNC, FUGR, INCL, VIEW). Falls back to a literal search when the pattern is not valid regex. | |
| name | No | Object name (e.g., ZTEST_PROGRAM, ZCL_ORDER, MARA) | |
| type | Yes | Object type to read (on-prem): PROG, CLAS, INTF, FUNC, FUGR, INCL, DDLS, DCLS, DDLX, BDEF, SRVD, SRVB, SKTD or KTD (Knowledge Transfer Documents), TABL (transparent tables and DDIC structures), TTYP, VIEW, DOMA, DTEL, MSAG, TRAN, TABLE_CONTENTS, TABLE_QUERY, DEVC, SOBJ, SYSTEM, COMPONENTS, TEXT_ELEMENTS, VARIANTS, BSP, BSP_DEPLOY, API_STATE, INACTIVE_OBJECTS, AUTH, FEATURE_TOGGLE, ENHO, VERSIONS, VERSION_SOURCE. Server-driven objects (discovery-gated; XML metadata; source is AFF JSON, or DDL text for DTSC/DSFD/DTDC): DESD (Logical External Schema), EVTB (RAP Event Binding), EVTO (RAP Event Object), DTSC (Static Cache), CSNM (CSN Model), COTA (Communication Target), DSFD (Scalar Function Def), DTDC (Dynamic Cache), UIAD (Launchpad App Descriptor Item). Deprecated aliases: MESSAGES (use MSAG), FTG2 (use FEATURE_TOGGLE). | |
| group | No | For FUNC/VERSIONS type. The function group containing the function module. Optional for FUNC — auto-resolved via SAPSearch if omitted. Required for VERSIONS when querying a function module revision feed. | |
| where | No | For TABLE_QUERY: structured WHERE conditions, ANDed together. Each item: {field, op, value?}. Ops: =, <>, <, <=, >, >=, LIKE, NOT LIKE, IN, NOT IN, IS NULL, IS NOT NULL; use <> because 758 rejects !=. For IN/NOT IN: use bare comma-separated values; do NOT quote them. ARC-1 quotes and escapes values, e.g. "261,262". No subqueries. Example: [{"field":"MATNR","op":"=","value":"300006888"},{"field":"BUDAT_MKPF","op":">=","value":"20250101"}]. | |
| action | No | Set to "diff" for a unified diff between two source versions (uses from/to) — cheaper than fetching both sources. Source types only: PROG, CLAS, INTF, FUNC, FUGR, INCL, DDLS, DCLS, BDEF, SRVD, DDLX, TABL. | |
| format | No | Default "text" (TABL/TTYP/DTEL/DOMA/INTF metadata included). DEVC: array in first text block + listing metadata in second; "structured" returns {objects, listing}. CLAS "structured": metadata + all includes; prefer method/grep for targeted reads. action="diff": "structured" returns JSON {hasDifferences, identical, added, removed, diff, version labels}; default is a patch. | |
| method | No | For CLAS: read a method (e.g., "get_name", "zif_order~process", "lhc_travel~accept") or use "*" to list methods. Without include=, lhc_*/lcl_* use implementations, ltc_* uses testclasses, and others use MAIN; explicit include= wins. For SOBJ: BOR method name to read. If omitted, returns the full BOR method catalog. Not used with other types. | |
| columns | No | For TABLE_QUERY: columns to SELECT (default: all). Example: ["MATNR","BWART","BUDAT","MENGE"]. | |
| include | No | CLAS: omit include or use main for the global declaration + implementation; definitions/implementations select local helper classes, macros/testclasses their own sections. Explicit include wins over method auto-routing. For DDLS: use include="elements" for the CDS field catalog (key fields, aliases, associations, expression types) instead of raw DDL. For VERSIONS (CLAS): include selects the class include history to query (main, definitions, implementations, macros, testclasses). BSP: case-sensitive path; name may also be APP/path. TEXT_ELEMENTS: symbols|selections|headings; omit for pool (CLAS: symbols). | |
| maxRows | No | Row cap for TABLE_CONTENTS/TABLE_QUERY (default 100, max 10,000; byte limit may apply sooner). On 758, TABLE_CONTENTS returns N+1; use TABLE_QUERY for exact caps. | |
| toLabel | No | action="diff" optional display label for the NEW side in the summary and patch header, e.g. "active" or "inactive draft". Does not affect source resolution. | |
| version | No | Version to read. Source: "active" (default); "inactive" requests the draft (SAP may return active if none); "auto" uses the developer view. DTEL: omitted/"auto" uses its developer view; explicit values pass through. | |
| fromLabel | No | action="diff" optional display label for the OLD side in the summary and patch header, e.g. "DNT-6-6: Validate discounts (DS7K900123)". Does not affect source resolution. | |
| sqlFilter | No | TABLE_CONTENTS condition expression only (no WHERE, no SELECT); broken on 758 (SAP expects SELECT). Use TABLE_QUERY where. | |
| maxResults | No | DEVC object limit (default 200, clamped to [1, 1000]). Listing metadata reports the effective limit and possible truncation. Total and full repository completeness remain unknown. | |
| objectType | No | For API_STATE and VERSIONS: SAP object type (CLAS, INTF, PROG, FUNC, INCL, DDLS, DCLS, BDEF, SRVD, etc.). For API_STATE: auto-detected from name if omitted. For VERSIONS: required to pick the correct revisions endpoint (e.g., "FUNC" + group for function modules); inferred from CL_/IF_/CX_ name prefixes when possible, defaults to PROG. TEXT_ELEMENTS: PROG (default), CLAS or FUGR. | |
| versionUri | No | VERSION_SOURCE: canonical source/revision URI from VERSIONS .revisions[].uri; rejects unrelated ADT endpoints, absolute URLs, traversal, queries, and fragments. | |
| force_refresh | No | For source reads: bypass cached source and inactive-list state before reading. Use when you know the object changed outside ARC-1. | |
| expand_includes | No | For FUGR type only. When true, recursively expands the function group include tree — the main source plus all nested INCLUDEs (the FUNCTION...ENDFUNCTION bodies live in nested LZ<grp>U01/U02 includes, so a flat one-level walk misses them). Each block is prefixed with a "=== name ===" marker; depth/count-capped. Dynpros and GUI status are not included (ADT does not expose them over REST). | |
| includeSignature | No | For FUNC type only. When true, response is JSON: {source, signature: {importing[], exporting[], changing[], tables[], exceptions[], raising[]}, processingType?, updateTaskKind?} — each parameter parsed into {kind, name, type, byValue?, default?, optional?}; processingType reports rfc/update/normal. Default false (returns plain source body). |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare readOnlyHint=true, so the description carries the burden of behavioral disclosure. It provides rich details: version fallback ('SAP may return active if none'), grep fallback to literal search, 758 TABLE_CONTENTS returns N+1, byte limits on maxRows, on-prem-only restrictions, deprecations, draft-existence notes, and force_refresh cache bypass. No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but front-loads the core purpose and the SAPContext alternative before diving into type-specific details. The type list is dense but necessary, and each sentence carries information (e.g., 'structured is CLAS-only for ordinary reads', 'Active source reads note when a draft exists'). It could benefit from bullet points, but it remains well-organized for the complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description covers return behaviors for grep (line numbers, context), diff (patch vs structured JSON), CLAS structured (metadata + all includes), FUNC includeSignature (JSON with signature arrays), and DEVC structured (objects + listing). It also specifies row caps, on-prem limitations, and version semantics. The only minor omission is a description of the default text return shape, but that is self-evident for source reads.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although schema coverage is 100%, the description adds significant interaction semantics not in the schema: method='*' lists signatures, explicit include wins over method auto-routing, lhc_*/lcl_* route to implementations, TABLE_QUERY ops must use <> because 758 rejects !=, and diff structured returns a JSON shape. It also explains the difference between TABLE_CONTENTS and TABLE_QUERY for filtering. This goes well beyond the schema's field-level descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource: 'Read SAP ABAP source or metadata.' It immediately distinguishes itself from SAPContext by noting 'For purpose, explanations, specs, reviews or pre-change context, prefer SAPContext first.' The long type list further specifies the exact kinds of resources it can read.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It provides explicit guidance to prefer SAPContext for purpose/explanation/spec/review/pre-change contexts, and gives conditional instructions such as 'AUTH/FEATURE_TOGGLE/ENHO/VERSIONS/VERSION_SOURCE are on-prem only' and 'do NOT combine with method=' for grep. It also explains when to use method vs grep, and when to use include='elements' for DDLS. However, it does not comprehensively map all sibling tools (e.g., SAPSearch, SAPLint) to usage scenarios, leaving some inference to the agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
SAPSearchARead-only
Search for ABAP objects, exact object-directory entries, or source code. Modes:
Object search (default): name pattern with wildcards (*); returns type, name, package, description, ADT URI.
TADIR lookup (searchType="tadir_lookup"): exact cross-package lookup of one or more names (prefer over long SAPQuery TADIR IN-lists). Tips: BOR objects appear as SOBJ; the uri field feeds SAPNavigate, objectType feeds SAPRead/SAPWrite/SAPActivate. Searches object NAMES only — for field names use SAPRead(type='DDLS', include='elements') or SAPQuery on DD03L.
| Name | Required | Description | Default |
|---|---|---|---|
| names | No | For tadir_lookup: exact object names to resolve across packages. Prefer this over long SAPQuery TADIR IN-lists. | |
| query | No | Search pattern for object search, or comma/whitespace-separated names for tadir_lookup. | |
| source | No | For tadir_lookup only: data source for the lookup. "adt" (default) uses the ADT info-system endpoint — workbench-resolvable objects only. "db" issues SQL against table TADIR — also surfaces orphan/ghost rows from aborted create-delete cycles (requires sql scope and SAP_ALLOW_FREE_SQL=true). "both" runs both paths and adds a "splitBrain" array listing names where the two sources disagree, plus a "warnings" array explaining each divergence (requires sql scope). | |
| maxResults | No | Maximum results (default 100) | |
| objectType | No | Object search: SAP-side type filter before the result limit (e.g., UIAC, CLAS, CLAS/OC). Source search: type filter (e.g., PROG, CLAS, FUNC). For tadir_lookup: single type filter; use objectTypes for multiple. | |
| searchType | No | Search mode: "object" (default) searches by object name, "tadir_lookup" does exact cross-package object lookup. | |
| objectTypes | No | For tadir_lookup: optional ADT/TADIR type filters (e.g., TABL, DDLS, BDEF, SRVB, CLAS/OC). |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation is already present, but the description adds substantial behavioral detail: the two search modes, default behavior, BOR-as-SOBJ mapping, return fields, and the differences among adt/db/both TADIR sources including splitBrain/warnings and the SQL-scope prerequisite. This goes well beyond the annotation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but every sentence earns its place: mode definitions, output fields, sibling routing, and gotchas are all decision-relevant. The length is justified by seven parameters and multiple modes, and the main purpose is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no output schema, it does well: object-search return fields are listed, TADIR source divergence is explained, and security prerequisites are mentioned. The main gap is that the first sentence advertises source-code search and objectType references a 'Source search', but the Modes list only defines object and tadir_lookup, leaving the agent to infer how source-code search is triggered.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds real cross-parameter meaning: it explains how searchType selects a mode, how names and query differ by mode, how objectType changes meaning between object and source search, and what source='both' produces. The parameter descriptions alone would not convey this integration.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource ('Search for ABAP objects, exact object-directory entries, or source code') and then names two distinct modes with different inputs and outputs. It also differentiates from siblings behaviorally by explaining that uri feeds SAPNavigate and objectType feeds SAPRead/SAPWrite/SAPActivate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says when to prefer TADIR lookup over long SAPQuery TADIR IN-lists, and it redirects field-name searches to SAPRead(type='DDLS', include='elements') or SAPQuery on DD03L. This is concrete when-to-use vs. when-not-to-use guidance, not just a vague hint.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
SAPTransportADestructive
Manage CTS transport requests (SE09/SE10). Actions: list (current user, modifiable), get (tasks + objects), create (always a Workbench (K) request — the package/target sets target & layer, not the request category; optional explicit target), release, delete, remove_object (keep the request), reassign (change owner), release_recursive (tasks then parent), check (does a package need a transport — type, name, package), history (legacy name: current object lock plus assignment candidates — type, name; not complete transport history; read-only, no write scope needed). IDs look like A4HK900123. Status: D/L=modifiable, O/P=releasing, R/N=released.
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | Transport request ID, e.g. A4HK900123 (required for get/diff/release/delete/reassign/release_recursive/remove_object) | |
| name | No | Object name (for check, history, or remove_object actions) | |
| type | No | Object type for check/history/remove_object actions (PROG, CLAS, DDLS, etc.). Not used by create, which creates a Workbench (K) request. | |
| user | No | List user (default: current SAP user; "*" means all visible owners). | |
| limit | No | diff: objects per call (default 20, max 40); page with offset. | |
| owner | No | New owner SAP username (required for reassign) | |
| pgmid | No | Program ID for remove_object: "R3TR" (whole object) or "LIMU" (sub-object). Required — object type alone does not determine pgmid. | |
| action | Yes | list: show transports (defaults to current user, modifiable only). Pass summary=true for a headers-only overview that omits each transport's object lists (keeps an objectCount) — far cheaper when many transports are open. get: fetch transport details including tasks and objects. diff: what a transport CHANGED — per object, the revision written under it vs the one before, as diff hunks (get only lists names). LIMU entries roll up to their class; an open transport compares to the last released revision. Read baselineStatus first: prior-revision = solid; prior-revision-unverified = pair guessed, may be another change; no-prior-snapshot = created here; baseline-ambiguous = no baseline, so an all-additions block is NOT proof of creation; baseline-unavailable = the read FAILED, never call that unchanged. create: create a new transport request (description required). To target another system, pass target=<system | system.client | /group/> (the Transportziel / TR_TARGET, e.g. "/TRG/" or "C11"; the group and system.client forms require extended transport control to be active). Otherwise omit target and pass an optional package to let SAP infer the route (defaults to $TMP). The response reports the resolved transport target; an empty target means a LOCAL request (cannot be transported onward). release: release a single transport or task. delete: delete a transport (use recursive=true to delete tasks first; removeLockedObjects=true to strip locked objects that otherwise block deletion with "...contains locked objects"). remove_object: remove one object from a request, keeping the request — needs the full key pgmid+type+name. reassign: change transport owner (use recursive=true for tasks too). release_recursive: release all unreleased tasks first, then the transport itself. check: check create/modify transport needs for a package/object (requires type, name, package; operation defaults to create). history: inspect the current object lock and assignment candidates (legacy action name; not complete transport history; requires type, name; works without SAP_ALLOW_TRANSPORT_WRITES). layers: list the transport layers this system offers (name + description + resolved target where any) — the valid values for create's transportLayer. Use this to discover a real value instead of guessing; works without SAP_ALLOW_TRANSPORT_WRITES. targets: list the valid transport targets (Transportziel / TR_TARGET) this system offers — the valid values for create's target. Use this to discover a real target (e.g. before create with target=). Read-only. Both report unavailability at runtime on releases that lack the value-help endpoint. | |
| offset | No | diff: first object to diff (default 0). | |
| status | No | Transport status filter (for list). D=modifiable (default), R=released, "*"=all statuses. | |
| target | No | Explicit transport target (Transportziel / TR_TARGET) for create — what the user means by "create a transport with target X". Forms: a system ("C11"), system.client ("C11.021"), or target group ("/TRG/"). The group and system.client forms require extended transport control (CTC) to be active. Created via the tm:root/newrequest endpoint (the only ADT path that sets the target directly) — this needs a newer ABAP Platform / S/4HANA; SAP_BASIS 7.50 rejects it with "user action is not supported" (an ADT-stack limitation, so set the target in SE09/SE10 there instead). SAP validates the target — an unknown target is rejected. Pass the exact value the user gives; do not invent one. | |
| package | No | Package name. For create: optional — defaults to $TMP; an explicit package influences the route/target, while the request remains Workbench type K. For check: required. | |
| summary | No | For list only. DEFAULT true: headers-only — drops each transport's (and task's) object lists, keeping id/description/owner/status/target + objectCount; use action="get" for one in full. Pass false for full object lists (~5x larger). | |
| operation | No | Check mode: create (default) or modify. | |
| recursive | No | Apply recursively to child tasks (for delete/reassign). release_recursive always recurses. | |
| maxResults | No | Maximum list rows or check/history assignment candidates (defaults: list/history 50, check 10; max 1000). | |
| description | No | Transport description text (required for create) | |
| resultFormat | No | release actions: legacy (default) or structured JSON. | |
| timeoutSeconds | No | release timeout seconds: 1-1800; default 300. | |
| transportLayer | No | Transport layer for create (optional, advanced). Sent as the ?transportLayer= query param to override which consolidation route — and therefore which target — SAP resolves. OMIT IT by default: SAP resolves the target from the package automatically, which is correct for almost all cases. Never invent a value — if you need a specific layer, obtain it from action="layers" or from the user. Only effective when that layer has a classic STMS consolidation route; otherwise the request is local regardless. | |
| removeLockedObjects | No | For delete only. Strip locked objects from each task before deleting, so a request that still holds a locked object (e.g. a deleted object's lingering record → HTTP 400 "...contains locked objects") can be removed. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description is exceptionally transparent about behavior. It warns of destructive actions (delete, release) and details how to control them (recursive, removeLockedObjects). It discloses limitations (e.g., history is not complete, create always produces K request, SAP_BASIS 7.50 limitation for target). It also distinguishes read-only operations (layers, targets) and notes permission requirements ('no write scope needed'). This goes far beyond the annotations (readOnlyHint=false, destructiveHint=true) and even enriches them with actionable context. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but well-structured: it opens with the overall purpose, then lists actions with embedded details, and includes status codes and caveats. Each sentence carries meaningful information; there is little fluff. While not as terse as the TDQS 4.3 example, it efficiently packs a large amount of necessary detail for a complex 21-parameter tool. The structure (action-by-action) aids scannability.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (21 parameters, 10+ actions, no output schema), the description is remarkably complete. It covers all actions, explains edge cases (e.g., $TMP default, extended transport control requirement, SAP_BASIS 7.50 fallback), provides return hints (e.g., 'response reports the resolved transport target'), and clarifies limitations (e.g., 'not complete transport history'). It effectively compensates for the missing output schema by describing expected results and failure modes.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed per-parameter descriptions. The tool description adds further semantic context, such as defaults ($TMP), interplay between parameters (package influences target), and validation rules (target must be valid). For example, the 'action' parameter in the schema is already long, but the description adds practical guidance on when to use summary=true and how to interpret diff baselines. This adds value beyond the schema, justifying a score above the baseline of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose as managing CTS transport requests (SE09/SE10) and enumerates specific actions (list, get, create, release, etc.). It uses a specific verb+resource pattern and differentiates from sibling tools like SAPRead or SAPManage by focusing on transport lifecycle operations. The explicit action list and status code explanation provide unambiguous scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear context for when to use the tool and its actions, e.g., 'check: check create/modify transport needs' and 'history: ... works without SAP_ALLOW_TRANSPORT_WRITES'. It also notes read-only actions (layers, targets) and explains trade-offs (e.g., summary=true for cheaper list). However, it does not explicitly compare against sibling tools or state 'use this instead of X', so it lacks explicit exclusions or alternatives. Still, context is clear enough for a 4.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
5 tool updates
v1.3.0- Changed
SAPContext2 fields changed- changed
Input schema / properties / action / descriptionPrevious value: -"Action:\n\"impact\" = CDS blast-radius analysis (DDLS only). USE THIS for any question like \"what breaks if I change <view>\", \"who consumes <I_*>\", \"impact analysis on <CDS>\", \"downstream of <view>\". Returns upstream AST dependencies + downstream where-used classified into RAP buckets (projectionViews, bdefs, serviceDefinitions, serviceBindings, accessControls, metadataExtensions, abapConsumers, documentation, tables, other), plus additive sibling-consistency diagnostics (consistencyHints + siblingExtensionAnalysis) when related DDLS siblings show asymmetric DDLX coverage. ALWAYS prefer over SAPQuery against DDDDLSRC/ACMDCLSRC/DDLXSRC_SRC/SRVDSRC_SRC (those text-scans produce noise this classifier filters out). Non-DDLS input returns a guardrail error.\n\"deps\" (default, can be omitted) = object understanding / forward dependency context — \"what does <object> do?\" or \"what does <object> depend on?\". Returns the object KTD when available plus public API contracts of dependencies.\n\"usages\" = live SAP where-used lookup. Provide \"type\" when known; without it, the name must resolve uniquely. Prefer \"impact\" for CDS.\n\"structure\" = TABL includes/appends."New value: +"Action:\n\"impact\" = CDS blast-radius analysis (DDLS only). USE THIS for any question like \"what breaks if I change <view>\", \"who consumes <I_*>\", \"impact analysis on <CDS>\", \"downstream of <view>\". Returns upstream AST dependencies + downstream where-used classified into RAP buckets (projectionViews, bdefs, serviceDefinitions, serviceBindings, accessControls, metadataExtensions, abapConsumers, documentation, tables, other), plus additive sibling-consistency diagnostics (consistencyHints + siblingExtensionAnalysis) when related DDLS siblings show asymmetric DDLX coverage. ALWAYS prefer over SAPQuery against DDDDLSRC/ACMDCLSRC/DDLXSRC_SRC/SRVDSRC_SRC (those text-scans produce noise this classifier filters out). Non-DDLS input returns a guardrail error.\n\"deps\" (default) = source-derived dependency contracts plus KTD when available. Requires type+name, even with source. Not a complete inventory; read source for behavior.\n\"usages\" = live SAP where-used lookup. Provide \"type\" when known; without it, the name must resolve uniquely. Prefer \"impact\" for CDS.\n\"structure\" = TABL includes/appends." - changed
Input schema / properties / type / descriptionPrevious value: -"Object type. Optional for action=\"impact\" (defaults to DDLS) or action=\"usages\"; required otherwise."New value: +"Root type. deps requires type+name, even with source. Optional for action=\"impact\" (defaults to DDLS) or usages (unique name lookup); structure requires TABL."
- Changed
SAPDiagnose34 fields changed- changed
Input schema / properties / action / enumPrevious value: -[ - "syntax", - "unittest", - "atc", - "atc_variants", - "cds_testcases", - "dumps", - "traces", - "trace_start", - "trace_requests", - "trace_cancel", - "system_messages", - "gateway_errors", - "object_state", - "quickfix", - "apply_quickfix", - "odata_perf", - "cds_sql", - "sql_trace_state", - "set_sql_trace_state", - "sql_trace_directory", - "authorization_trace" -]New value: +[ + "syntax", + "unittest", + "unittest_ci", + "atc", + "atc_ci", + "atc_variants", + "cds_testcases", + "dumps", + "traces", + "trace_start", + "trace_requests", + "trace_cancel", + "system_messages", + "gateway_errors", + "object_state", + "quickfix", + "apply_quickfix", + "odata_perf", + "cds_sql", + "sql_trace_state", + "set_sql_trace_state", + "sql_trace_directory", + "authorization_trace" +] - changed
Input schema / properties / aggregate / descriptionPrevious value: -"For trace_start: aggregate the trace (default true)."New value: +"trace_start aggregation (default true)." - changed
Input schema / properties / analysis / descriptionPrevious value: -"Trace analysis type (for traces action with id). hitlist = execution hot spots, statements = call tree, dbAccesses = database access stats."New value: +"traces with id: hitlist=hot spots, statements=call tree, dbAccesses=DB access stats." - changed
Input schema / properties / column / descriptionPrevious value: -"Source column number for quickfix evaluation (default 0 for quickfix actions)."New value: +"Quickfix source column (default 0)." - added
Input schema / properties / configurationAdded value: +{ + "description": "atc_ci: optional configuration.", + "maxLength": 128, + "minLength": 1, + "type": "string" +} - changed
Input schema / properties / description / descriptionPrevious value: -"For trace_start: optional label for the trace request."New value: +"trace_start label." - changed
Input schema / properties / detailUrl / descriptionPrevious value: -"Canonical host-relative /sap/bc/adt/gw/errorlog/... path for detail mode; absolute URLs are rejected."New value: +"Detail path: canonical /sap/bc/adt/gw/errorlog/...; no absolute URLs." - changed
Input schema / properties / errorType / descriptionPrevious value: -"Gateway error type for gateway_errors detail by id (for example \"Frontend Error\"). Required when using id without detailUrl."New value: +"gateway_errors: required with id instead of detailUrl, e.g. \"Frontend Error\"." - changed
Input schema / properties / expiresHours / descriptionPrevious value: -"For trace_start: hours until the armed request auto-expires (default 24)."New value: +"trace_start expiry in hours (default 24)." - added
Input schema / properties / failOnSeverityAdded value: +{ + "description": "atc_ci failure threshold (default error).", + "enum": [ + "error", + "warning", + "info" + ], + "type": "string" +} - changed
Input schema / properties / from / descriptionPrevious value: -"Optional lower time boundary for feed-based diagnostics actions (system_messages/gateway_errors)."New value: +"system_messages/gateway_errors lower time bound." - changed
Input schema / properties / includeFullText / descriptionPrevious value: -"For dumps detail mode only: include full formattedText blob. Default false to reduce token usage."New value: +"dumps detail: include full formattedText (default false)." - added
Input schema / properties / includeReportXmlAdded value: +{ + "description": "CI XML reports (default false; 256 KiB total cap).", + "type": "boolean" +} - changed
Input schema / properties / line / descriptionPrevious value: -"Source line number for quickfix evaluation (required for quickfix/apply_quickfix)."New value: +"Required quickfix/apply_quickfix source line." - changed
Input schema / properties / maxExecutions / descriptionPrevious value: -"For trace_start: how many matching executions to capture before the request is consumed (default 1)."New value: +"trace_start executions to capture (default 1)." - changed
Input schema / properties / maxResults / descriptionPrevious value: -"Maximum results for dumps/system_messages/gateway_errors (default 50) or authorization_trace (default 100); bounded to a safe cap."New value: +"Result limit: dumps/system_messages/gateway_errors default 50; authorization_trace 100. Capped." - changed
Input schema / properties / name / descriptionPrevious value: -"Object name (for syntax/unittest/atc/object_state); the CDS entity / DDLS source name for cds_testcases and cds_sql"New value: +"syntax/unittest/atc/object_state object name; cds_testcases/cds_sql CDS entity or DDLS name." - changed
Input schema / properties / objectType / descriptionPrevious value: -"For trace_start: what to match within the process. Defaults to the valid type for the process type (http→url, dialog→transaction, batch→report, rfc→functionModule)."New value: +"trace_start match type; defaults: http→url, dialog→transaction, batch→report, rfc→functionModule." - added
Input schema / properties / objectsAdded value: +{ + "description": "ATC only, instead of name/type/url. One batch + at most one verification. Returns coverage; unreported objects stay incomplete. No packages.", + "items": { + "additionalProperties": false, + "properties": { + "name": { + "maxLength": 40, + "minLength": 1, + "pattern": "^(?:/[A-Za-z0-9_]+/)?[A-Za-z0-9_]+$", + "type": "string" + }, + "type": { + "enum": [ + "CLAS", + "INTF", + "PROG", + "FUGR", + "DDLS", + "DCLS", + "BDEF", + "DDLX", + "SRVD", + "SRVB", + "TABL", + "DTEL", + "DOMA" + ], + "type": "string" + } + }, + "required": [ + "type", + "name" + ], + "type": "object" + }, + "maxItems": 20, + "minItems": 1, + "type": "array" +} - changed
Input schema / properties / onlyFailures / descriptionPrevious value: -"For authorization_trace: return only denied checks (RC<>0), similar to the SU53 failure view."New value: +"authorization_trace: only denied checks (RC<>0), like SU53." - added
Input schema / properties / packageTreesAdded value: +{ + "description": "CI packages including subpackages.", + "items": { + "maxLength": 40, + "minLength": 1, + "pattern": "^[A-Za-z0-9_/$]+$", + "type": "string" + }, + "maxItems": 50, + "type": "array" +} - added
Input schema / properties / packagesAdded value: +{ + "description": "CI exact packages; 1–50 total with packageTrees.", + "items": { + "maxLength": 40, + "minLength": 1, + "pattern": "^[A-Za-z0-9_/$]+$", + "type": "string" + }, + "maxItems": 50, + "type": "array" +} - changed
Input schema / properties / processType / descriptionPrevious value: -"For trace_start: the kind of work process to capture. Default \"http\" (OData/Gateway). dialog = SAP GUI transaction, batch = background job, rfc = RFC call."New value: +"trace_start work process (default http/OData): dialog=SAP GUI, batch=background job, rfc=RFC." - changed
Input schema / properties / proposalAffectedObjects / descriptionPrevious value: -"Optional affectedObjects array from quickfix action. Include content for each affected source unit when applying multi-object quickfixes."New value: +"quickfix affectedObjects; provide current content for each source unit when applying multi-object fixes." - changed
Input schema / properties / sections / descriptionPrevious value: -"Dump chapter IDs to include for dumps detail mode (for example [\"kap0\",\"kap3\",\"kap8\"]). Omit to use focused defaults."New value: +"dumps detail chapter IDs, e.g. [\"kap0\",\"kap3\",\"kap8\"]; omit for focused defaults." - changed
Input schema / properties / sourceUri / descriptionPrevious value: -"Exact ADT source URI for quickfix/apply_quickfix. Defaults to the type/name main source; use this for class includes such as /includes/definitions."New value: +"quickfix/apply_quickfix source URI; default type/name main source. Set for includes, e.g. /includes/definitions." - changed
Input schema / properties / sqlOn / descriptionPrevious value: -"For action=\"set_sql_trace_state\": true to arm the ST05 SQL trace, false to disarm. Combine with user to filter the trace to one SAP user."New value: +"set_sql_trace_state: true arms ST05 SQL trace, false disarms; user filters the SAP user." - changed
Input schema / properties / sqlTrace / descriptionPrevious value: -"For trace_start: capture SQL/DB accesses (default true — required for analysis=\"dbAccesses\")."New value: +"trace_start SQL capture (default true; required for analysis=\"dbAccesses\")." - changed
Input schema / properties / timeoutSeconds / descriptionPrevious value: -"unittest/atc timeout: 1-3600s; default 300."New value: +"Timeout 1–3600s: unittest/atc default 300; CI overall default 600." - changed
Input schema / properties / to / descriptionPrevious value: -"Optional upper time boundary for feed-based diagnostics actions (system_messages/gateway_errors)."New value: +"system_messages/gateway_errors upper time bound." - changed
Input schema / properties / traceUser / descriptionPrevious value: -"For trace_start/trace_requests: the SAP user whose matching execution is traced/listed. Defaults to the connected user."New value: +"trace_start/trace_requests SAP user (default connected user)." - changed
Input schema / properties / url / descriptionPrevious value: -"For odata_perf: the host-relative OData path to probe, from the Fiori app's Network tab (e.g. \"/sap/opu/odata4/sap/.../Entity?$filter=…\"). Must be a path on the connected system — absolute URLs are rejected."New value: +"odata_perf: host-relative OData path from the app network request (e.g. /sap/opu/odata4/sap/.../Entity?$filter=…). Absolute URLs rejected." - changed
Input schema / properties / variant / descriptionPrevious value: -"atc: check variant; atc_variants: name filter (*=all)"New value: +"atc/atc_ci variant; atc_variants name filter (*=all)" - changed
Input schema / properties / version / descriptionPrevious value: -"Source version for syntax check (default \"active\"). Use \"inactive\" to validate pending changes."New value: +"syntax source version (default active); inactive checks pending changes."
- Changed
SAPNavigate7 fields changed- changed
Input schema / properties / action / enumPrevious value: -[ - "definition", - "references", - "completion", - "hierarchy" -]New value: +[ + "definition", + "references", + "completion", + "hierarchy", + "relations" +] - added
Input schema / properties / depthAdded value: +{ + "description": "relations: native steps (default 1), not source-call hops.", + "maximum": 3, + "minimum": 1, + "type": "integer" +} - added
Input schema / properties / directionAdded value: +{ + "description": "relations: incoming=users; outgoing=dependencies (default).", + "enum": [ + "incoming", + "outgoing" + ], + "type": "string" +} - added
Input schema / properties / expandPackagesAdded value: +{ + "description": "relations: expand exact packages beyond root; others visible. Not authorization.", + "items": { + "maxLength": 120, + "minLength": 1, + "pattern": "^(?:/[A-Za-z0-9_]+/)?[A-Za-z0-9_$]+$", + "type": "string" + }, + "maxItems": 8, + "type": "array" +} - changed
Input schema / properties / maxResults / descriptionPrevious value: -"references: max entries (default 100, max 1000). \"total\" counts every match of the filter."New value: +"references: max entries (default 100, max 1000). \"total\" counts every match of the filter. relations: node cap incl. root, 1–100 (default 50); may stop earlier." - changed
Input schema / properties / objectType / descriptionPrevious value: -"references: keep only results of this ADT type, slash format (CLAS/OC, PROG/P, FUGR/FF). A bare prefix (\"CLAS\") matches every subtype."New value: +"references RESULT filter, not the root type: CLAS/OC, PROG/P, FUGR/FF. Omit for all consumer types. A bare prefix (\"CLAS\") matches every subtype." - changed
Input schema / properties / type / descriptionPrevious value: -"Object type (PROG, CLAS, INTF, FUNC, etc.) — alternative to uri for references."New value: +"Root object type, paired with name instead of uri (e.g. type=\"INTF\"). Not the result-type filter. relations: CLAS, INTF, DDLS, DCLS, BDEF, SRVD, TABL, TTYP, DTEL, DOMA, PROG, INCL, FUGR, FUNC, VIEW, ENHO, MSAG, TRAN, SHLP, SKTD, ENHS, ENQU, TYPE, EVTB, DSFD. ENHO/XHB, ENHS/XSB only; TTYP=table type; MSAG=message class."
- Changed
SAPRead7 fields changed- changed
Input schema / properties / format / descriptionPrevious value: -"Output format. For action=\"diff\", \"structured\" returns JSON {hasDifferences, identical, added, removed, diff, version labels}; default remains the human-readable patch. For ordinary reads, \"text\" (default) is raw source; \"structured\" (CLAS only) returns JSON metadata + EVERY class include — a superset of \"text\", so it always costs MORE (measured +10% to +1685%). Use only to split test from production code; otherwise method=\"*\" / method=\"name\" / grep=."New value: +"Default \"text\" (TABL/TTYP/DTEL/DOMA/INTF metadata included). DEVC: array in first text block + listing metadata in second; \"structured\" returns {objects, listing}. CLAS \"structured\": metadata + all includes; prefer method/grep for targeted reads. action=\"diff\": \"structured\" returns JSON {hasDifferences, identical, added, removed, diff, version labels}; default is a patch." - changed
Input schema / properties / include / descriptionPrevious value: -"For CLAS: DO NOT use this to read the main class — omit include entirely to get the full class source (CLASS DEFINITION + CLASS IMPLEMENTATION). This parameter reads class-LOCAL auxiliary files only: definitions (local type definitions, NOT the main class definition), implementations (local helper class implementations), macros, testclasses (ABAP Unit). Comma-separated. For DDLS: use include=\"elements\" for the CDS field catalog (key fields, aliases, associations, expression types) instead of raw DDL. For VERSIONS (CLAS): include selects the class include history to query (main, definitions, implementations, macros, testclasses)."New value: +"CLAS: omit include or use main for the global declaration + implementation; definitions/implementations select local helper classes, macros/testclasses their own sections. Explicit include wins over method auto-routing. For DDLS: use include=\"elements\" for the CDS field catalog (key fields, aliases, associations, expression types) instead of raw DDL. For VERSIONS (CLAS): include selects the class include history to query (main, definitions, implementations, macros, testclasses). BSP: case-sensitive path; name may also be APP/path. TEXT_ELEMENTS: symbols|selections|headings; omit for pool (CLAS: symbols)." - changed
Input schema / properties / maxResults / descriptionPrevious value: -"For DEVC: max number of objects to list (default 200, clamped to [1, 1000]). Larger packages may be silently truncated by SAP at this limit; raise it if needed."New value: +"DEVC object limit (default 200, clamped to [1, 1000]). Listing metadata reports the effective limit and possible truncation. Total and full repository completeness remain unknown." - changed
Input schema / properties / maxRows / descriptionPrevious value: -"Row cap (default 100). On 758, TABLE_CONTENTS returns N+1; use TABLE_QUERY or cap client-side."New value: +"Row cap for TABLE_CONTENTS/TABLE_QUERY (default 100, max 10,000; byte limit may apply sooner). On 758, TABLE_CONTENTS returns N+1; use TABLE_QUERY for exact caps." - changed
Input schema / properties / method / descriptionPrevious value: -"For CLAS: method name to read a single method implementation (e.g., \"get_name\", \"zif_order~process\"). Use \"*\" to list all methods with signatures and visibility. For SOBJ: BOR method name to read. If omitted, returns the full BOR method catalog. Not used with other types."New value: +"For CLAS: read a method (e.g., \"get_name\", \"zif_order~process\", \"lhc_travel~accept\") or use \"*\" to list methods. Without include=, lhc_*/lcl_* use implementations, ltc_* uses testclasses, and others use MAIN; explicit include= wins. For SOBJ: BOR method name to read. If omitted, returns the full BOR method catalog. Not used with other types." - changed
Input schema / properties / objectType / descriptionPrevious value: -"For API_STATE and VERSIONS: SAP object type (CLAS, INTF, PROG, FUNC, INCL, DDLS, DCLS, BDEF, SRVD, etc.). For API_STATE: auto-detected from name if omitted. For VERSIONS: required to pick the correct revisions endpoint (e.g., \"FUNC\" + group for function modules); inferred from CL_/IF_/CX_ name prefixes when possible, defaults to PROG."New value: +"For API_STATE and VERSIONS: SAP object type (CLAS, INTF, PROG, FUNC, INCL, DDLS, DCLS, BDEF, SRVD, etc.). For API_STATE: auto-detected from name if omitted. For VERSIONS: required to pick the correct revisions endpoint (e.g., \"FUNC\" + group for function modules); inferred from CL_/IF_/CX_ name prefixes when possible, defaults to PROG. TEXT_ELEMENTS: PROG (default), CLAS or FUGR." - changed
Input schema / properties / version / descriptionPrevious value: -"Source version to read. \"active\" (default) returns the last activated version. \"inactive\" returns the user's unactivated draft or active if no draft exists. \"auto\" returns the draft if one exists, else active."New value: +"Version to read. Source: \"active\" (default); \"inactive\" requests the draft (SAP may return active if none); \"auto\" uses the developer view. DTEL: omitted/\"auto\" uses its developer view; explicit values pass through."
- Changed
SAPSearch2 fields changed- changed
Input schema / properties / objectType / descriptionPrevious value: -"For source_code search: filter by object type (e.g., PROG, CLAS, FUNC). For tadir_lookup: single type filter; use objectTypes for multiple."New value: +"Object search: SAP-side type filter before the result limit (e.g., UIAC, CLAS, CLAS/OC). Source search: type filter (e.g., PROG, CLAS, FUNC). For tadir_lookup: single type filter; use objectTypes for multiple." - added
Input schema / properties / objectType / maxLengthAdded value: +64
3 tool updates
v1.1.0- Changed
SAPDiagnose7 fields changed- removed
Input schema / properties / action / descriptionRemoved value: -"Diagnostic action" - changed
Input schema / properties / coverage / descriptionPrevious value: -"For action=\"unittest\": also return statement/branch/procedure coverage for the object, plus methodsBelowFull — the methods below 100% statement coverage, worst first (what to test next) — in one extra round-trip. If the coverage endpoint or measurement is unavailable, returns the tests without coverage. Default false."New value: +"unittest only: collect statement/branch/procedure coverage and methodsBelowFull. Unavailable measurements do not discard test results. Default false." - changed
Input schema / properties / detailUrl / descriptionPrevious value: -"ADT detail URL for gateway_errors detail mode (preferred over id+errorType). Accepts absolute or /sap/bc/adt/... path."New value: +"Canonical host-relative /sap/bc/adt/gw/errorlog/... path for detail mode; absolute URLs are rejected." - added
Input schema / properties / includeSubpackagesAdded value: +{ + "default": false, + "type": "boolean" +} - added
Input schema / properties / resultFormatAdded value: +{ + "description": "unittest: legacy|structured|junit; atc: legacy|structured; other actions reject it.", + "enum": [ + "legacy", + "structured", + "junit" + ], + "type": "string" +} - added
Input schema / properties / timeoutSecondsAdded value: +{ + "description": "unittest/atc timeout: 1-3600s; default 300.", + "type": "number" +} - changed
Input schema / properties / type / descriptionPrevious value: -"Object type (PROG, CLAS, etc.) (for syntax/unittest/atc/object_state)"New value: +"Object type; unittest accepts CLAS, PROG, FUGR, or DEVC."
- Changed
SAPRead5 fields changed- changed
Input schema / properties / format / descriptionPrevious value: -"Output format. \"text\" (default): raw source. \"structured\" (CLAS only): JSON metadata + EVERY class include (main, testclasses, definitions, implementations, macros) — a superset of \"text\", so it always costs MORE (measured +10% to +1685%). Use only to split test from production code; otherwise method=\"*\" / method=\"name\" / grep=."New value: +"Output format. For action=\"diff\", \"structured\" returns JSON {hasDifferences, identical, added, removed, diff, version labels}; default remains the human-readable patch. For ordinary reads, \"text\" (default) is raw source; \"structured\" (CLAS only) returns JSON metadata + EVERY class include — a superset of \"text\", so it always costs MORE (measured +10% to +1685%). Use only to split test from production code; otherwise method=\"*\" / method=\"name\" / grep=." - changed
Input schema / properties / maxRows / descriptionPrevious value: -"For TABLE_CONTENTS and TABLE_QUERY: max rows to return (default 100)"New value: +"Row cap (default 100). On 758, TABLE_CONTENTS returns N+1; use TABLE_QUERY or cap client-side." - changed
Input schema / properties / sqlFilter / descriptionPrevious value: -"For TABLE_CONTENTS: condition expression only (no WHERE, no SELECT), e.g. \"MANDT = '100'\" or \"MATNR LIKE 'Z%'\"."New value: +"TABLE_CONTENTS condition expression only (no WHERE, no SELECT); broken on 758 (SAP expects SELECT). Use TABLE_QUERY where." - changed
Input schema / properties / versionUri / descriptionPrevious value: -"For VERSION_SOURCE: URI of a specific revision from SAPRead(type=\"VERSIONS\") response (.revisions[].uri). Must start with /sap/bc/adt/."New value: +"VERSION_SOURCE: canonical source/revision URI from VERSIONS .revisions[].uri; rejects unrelated ADT endpoints, absolute URLs, traversal, queries, and fragments." - changed
Input schema / properties / where / descriptionPrevious value: -"For TABLE_QUERY: structured WHERE conditions, ANDed together. Each item: {field, op, value?}. Allowed ops: =, !=, <>, <, <=, >, >=, LIKE, NOT LIKE, IN, NOT IN, IS NULL, IS NOT NULL. For IN/NOT IN: value must be a comma-separated list of single-quoted literals, e.g. \"'261','262'\". Subqueries are not allowed. Example: [{\"field\":\"MATNR\",\"op\":\"=\",\"value\":\"300006888\"},{\"field\":\"BUDAT_MKPF\",\"op\":\">=\",\"value\":\"20250101\"}]."New value: +"For TABLE_QUERY: structured WHERE conditions, ANDed together. Each item: {field, op, value?}. Ops: =, <>, <, <=, >, >=, LIKE, NOT LIKE, IN, NOT IN, IS NULL, IS NOT NULL; use <> because 758 rejects !=. For IN/NOT IN: use bare comma-separated values; do NOT quote them. ARC-1 quotes and escapes values, e.g. \"261,262\". No subqueries. Example: [{\"field\":\"MATNR\",\"op\":\"=\",\"value\":\"300006888\"},{\"field\":\"BUDAT_MKPF\",\"op\":\">=\",\"value\":\"20250101\"}]."
- Changed
SAPTransport8 fields changed- changed
Input schema / properties / action / descriptionPrevious value: -"list: show transports (defaults to current user, modifiable only). Pass summary=true for a headers-only overview that omits each transport's object lists (keeps an objectCount) — far cheaper when many transports are open. get: fetch transport details including tasks and objects. create: create a new transport request (description required). To target another system, pass target=<system | system.client | /group/> (the Transportziel / TR_TARGET, e.g. \"/TRG/\" or \"C11\"; the group and system.client forms require extended transport control to be active). Otherwise omit target and pass an optional package to let SAP infer the route (defaults to $TMP). The response reports the resolved transport target; an empty target means a LOCAL request (cannot be transported onward). release: release a single transport or task. delete: delete a transport (use recursive=true to delete tasks first; removeLockedObjects=true to strip locked objects that otherwise block deletion with \"...contains locked objects\"). remove_object: remove one object from a request, keeping the request — needs the full key pgmid+type+name. reassign: change transport owner (use recursive=true for tasks too). release_recursive: release all unreleased tasks first, then the transport itself. check: check create/modify transport needs for a package/object (requires type, name, package; operation defaults to create). history: inspect the current object lock and assignment candidates (legacy action name; not complete transport history; requires type, name; works without SAP_ALLOW_TRANSPORT_WRITES). layers: list the transport layers this system offers (name + description + resolved target where any) — the valid values for create's transportLayer. Use this to discover a real value instead of guessing; works without SAP_ALLOW_TRANSPORT_WRITES. targets: list the valid transport targets (Transportziel / TR_TARGET) this system offers — the valid values for create's target. Use this to discover a real target (e.g. before create with target=). Read-only. Both report unavailability at runtime on releases that lack the value-help endpoint."New value: +"list: show transports (defaults to current user, modifiable only). Pass summary=true for a headers-only overview that omits each transport's object lists (keeps an objectCount) — far cheaper when many transports are open. get: fetch transport details including tasks and objects. diff: what a transport CHANGED — per object, the revision written under it vs the one before, as diff hunks (get only lists names). LIMU entries roll up to their class; an open transport compares to the last released revision. Read baselineStatus first: prior-revision = solid; prior-revision-unverified = pair guessed, may be another change; no-prior-snapshot = created here; baseline-ambiguous = no baseline, so an all-additions block is NOT proof of creation; baseline-unavailable = the read FAILED, never call that unchanged. create: create a new transport request (description required). To target another system, pass target=<system | system.client | /group/> (the Transportziel / TR_TARGET, e.g. \"/TRG/\" or \"C11\"; the group and system.client forms require extended transport control to be active). Otherwise omit target and pass an optional package to let SAP infer the route (defaults to $TMP). The response reports the resolved transport target; an empty target means a LOCAL request (cannot be transported onward). release: release a single transport or task. delete: delete a transport (use recursive=true to delete tasks first; removeLockedObjects=true to strip locked objects that otherwise block deletion with \"...contains locked objects\"). remove_object: remove one object from a request, keeping the request — needs the full key pgmid+type+name. reassign: change transport owner (use recursive=true for tasks too). release_recursive: release all unreleased tasks first, then the transport itself. check: check create/modify transport needs for a package/object (requires type, name, package; operation defaults to create). history: inspect the current object lock and assignment candidates (legacy action name; not complete transport history; requires type, name; works without SAP_ALLOW_TRANSPORT_WRITES). layers: list the transport layers this system offers (name + description + resolved target where any) — the valid values for create's transportLayer. Use this to discover a real value instead of guessing; works without SAP_ALLOW_TRANSPORT_WRITES. targets: list the valid transport targets (Transportziel / TR_TARGET) this system offers — the valid values for create's target. Use this to discover a real target (e.g. before create with target=). Read-only. Both report unavailability at runtime on releases that lack the value-help endpoint." - changed
Input schema / properties / action / enumPrevious value: -[ - "list", - "get", - "check", - "history", - "layers", - "targets" -]New value: +[ + "list", + "get", + "diff", + "check", + "history", + "layers", + "targets" +] - changed
Input schema / properties / id / descriptionPrevious value: -"Transport request ID, e.g. A4HK900123 (required for get/release/delete/reassign/release_recursive/remove_object)"New value: +"Transport request ID, e.g. A4HK900123 (required for get/diff/release/delete/reassign/release_recursive/remove_object)" - added
Input schema / properties / limitAdded value: +{ + "description": "diff: objects per call (default 20, max 40); page with offset.", + "type": "number" +} - added
Input schema / properties / offsetAdded value: +{ + "description": "diff: first object to diff (default 0).", + "type": "number" +} - added
Input schema / properties / resultFormatAdded value: +{ + "description": "release actions: legacy (default) or structured JSON.", + "enum": [ + "legacy", + "structured" + ], + "type": "string" +} - added
Input schema / properties / timeoutSecondsAdded value: +{ + "description": "release timeout seconds: 1-1800; default 300.", + "type": "number" +} - changed
Input schema / properties / user / descriptionPrevious value: -"SAP user for list (default: current user; \"*\" means all users)."New value: +"List user (default: current SAP user; \"*\" means all visible owners)."
8 tool updates
v1.0.2- Changed
SAPContext7 fields changed- added
Input schema / additionalPropertiesAdded value: +false - changed
Input schema / properties / includeIndirect / descriptionPrevious value: -"Only for action=\"impact\". Include indirect (transitive) downstream where-used entries. Default false."New value: +"impact: Include indirect (transitive) downstream where-used entries. Default false." - changed
Input schema / properties / includeKtd / descriptionPrevious value: -"Only for action=\"deps\". When true/default, prepend the object Knowledge Transfer Document (KTD/SKTD) when one exists. Set false to skip the KTD lookup."New value: +"deps: When true/default, prepend the object Knowledge Transfer Document (KTD/SKTD) when one exists. Set false to skip the KTD lookup." - changed
Input schema / properties / maxDeps / descriptionPrevious value: -"Maximum dependencies to resolve (default 20). Lower = faster + fewer tokens."New value: +"Max dependencies to resolve (default 20). Lower = faster + fewer tokens." - added
Input schema / properties / maxResultsAdded value: +{ + "description": "usages: max entries (default 100); impact: max per downstream bucket (default 50). Max 1000. \"usageCount\"/\"summary\" stay true totals, not page sizes.", + "type": "number" +} - changed
Input schema / properties / siblingCheck / descriptionPrevious value: -"Only for action=\"impact\". Enable sibling metadata-extension consistency analysis. Default true."New value: +"impact: Enable sibling metadata-extension consistency analysis. Default true." - changed
Input schema / properties / siblingMaxCandidates / descriptionPrevious value: -"Only for action=\"impact\". Maximum sibling DDLS candidates to compare. Default 4; hard cap 10."New value: +"impact: Maximum sibling DDLS candidates to compare. Default 4; hard cap 10."
- Changed
SAPDiagnose3 fields changed- added
Input schema / additionalPropertiesAdded value: +false - changed
Input schema / properties / action / enumPrevious value: -[ - "syntax", - "unittest", - "atc", - "cds_testcases", - "dumps", - "traces", - "trace_start", - "trace_requests", - "trace_cancel", - "system_messages", - "gateway_errors", - "object_state", - "quickfix", - "apply_quickfix", - "odata_perf", - "cds_sql", - "sql_trace_state", - "set_sql_trace_state", - "sql_trace_directory", - "authorization_trace" -]New value: +[ + "syntax", + "unittest", + "atc", + "atc_variants", + "cds_testcases", + "dumps", + "traces", + "trace_start", + "trace_requests", + "trace_cancel", + "system_messages", + "gateway_errors", + "object_state", + "quickfix", + "apply_quickfix", + "odata_perf", + "cds_sql", + "sql_trace_state", + "set_sql_trace_state", + "sql_trace_directory", + "authorization_trace" +] - changed
Input schema / properties / variant / descriptionPrevious value: -"ATC check variant (for atc action)"New value: +"atc: check variant; atc_variants: name filter (*=all)"
- Changed
SAPLint1 field changed- added
Input schema / additionalPropertiesAdded value: +false
- Changed
SAPManage2 fields changed- added
Input schema / additionalPropertiesAdded value: +false - changed
Input schema / properties / responsible / descriptionPrevious value: -"BTP only: the internal ABAP user (XUBNAME, e.g. CB9980000000) for the new package person-responsible. Auto-resolved from prior object creates if omitted; the IAS email is rejected."New value: +"Person-responsible: an existing ABAP user (XUBNAME, max 12 chars); an email is rejected. Defaults to the connection user; pass explicitly under principal propagation. BTP: auto-resolved from prior creates."
- Changed
SAPNavigate3 fields changed- added
Input schema / additionalPropertiesAdded value: +false - added
Input schema / properties / maxResultsAdded value: +{ + "description": "references: max entries (default 100, max 1000). \"total\" counts every match of the filter.", + "type": "number" +} - changed
Input schema / properties / objectType / descriptionPrevious value: -"For references action: filter where-used results by ADT object type in slash format (e.g., PROG/P, CLAS/OC, FUGR/FF, INTF/OI). On systems supporting the scope endpoint, only returns references from objects of the specified type. On older systems, the filter is ignored and all references are returned with a note."New value: +"references: keep only results of this ADT type, slash format (CLAS/OC, PROG/P, FUGR/FF). A bare prefix (\"CLAS\") matches every subtype."
- Changed
SAPRead6 fields changed- added
Input schema / additionalPropertiesAdded value: +false - changed
Input schema / properties / format / descriptionPrevious value: -"Output format. \"text\" (default): raw source code. \"structured\" (CLAS only): JSON with metadata (description, language, category) + decomposed source (main, testclasses, definitions, implementations, macros). Useful when you need to understand class structure or separate test code from production code."New value: +"Output format. \"text\" (default): raw source. \"structured\" (CLAS only): JSON metadata + EVERY class include (main, testclasses, definitions, implementations, macros) — a superset of \"text\", so it always costs MORE (measured +10% to +1685%). Use only to split test from production code; otherwise method=\"*\" / method=\"name\" / grep=." - changed
Input schema / properties / include / descriptionPrevious value: -"For CLAS: DO NOT use this to read the main class — omit include entirely to get the full class source (CLASS DEFINITION + CLASS IMPLEMENTATION). This parameter reads class-LOCAL auxiliary files only: definitions (local type definitions, NOT the main class definition), implementations (local helper class implementations), macros, testclasses (ABAP Unit). Comma-separated. Not all classes have these sections — missing ones return a note instead of an error. For DDLS: use include=\"elements\" to get a structured field list extracted from the CDS DDL source — shows key fields, aliases, associations, and expression types (calculated, case, cast). Useful for understanding CDS entity structure without parsing raw DDL. For VERSIONS (CLAS): include selects the class include history to query (main, definitions, implementations, macros, testclasses)."New value: +"For CLAS: DO NOT use this to read the main class — omit include entirely to get the full class source (CLASS DEFINITION + CLASS IMPLEMENTATION). This parameter reads class-LOCAL auxiliary files only: definitions (local type definitions, NOT the main class definition), implementations (local helper class implementations), macros, testclasses (ABAP Unit). Comma-separated. For DDLS: use include=\"elements\" for the CDS field catalog (key fields, aliases, associations, expression types) instead of raw DDL. For VERSIONS (CLAS): include selects the class include history to query (main, definitions, implementations, macros, testclasses)." - changed
Input schema / properties / includeSignature / descriptionPrevious value: -"For FUNC type only. When true, response is JSON: {source, signature: {importing[], exporting[], changing[], tables[], exceptions[], raising[]}} — each parameter parsed into {kind, name, type, byValue?, default?, optional?}. Default false (returns plain source body). Use this to introspect FM parameter signatures programmatically without re-parsing ABAP."New value: +"For FUNC type only. When true, response is JSON: {source, signature: {importing[], exporting[], changing[], tables[], exceptions[], raising[]}, processingType?, updateTaskKind?} — each parameter parsed into {kind, name, type, byValue?, default?, optional?}; processingType reports rfc/update/normal. Default false (returns plain source body)." - changed
Input schema / properties / type / descriptionPrevious value: -"Object type to read (on-prem): PROG, CLAS, INTF, FUNC, FUGR, INCL, DDLS, DCLS, DDLX, BDEF, SRVD, SRVB, SKTD or KTD (Knowledge Transfer Documents), TABL (transparent tables and DDIC structures), VIEW, DOMA, DTEL, MSAG, TRAN, TABLE_CONTENTS, TABLE_QUERY, DEVC, SOBJ, SYSTEM, COMPONENTS, TEXT_ELEMENTS, VARIANTS, BSP, BSP_DEPLOY, API_STATE, INACTIVE_OBJECTS, AUTH, FEATURE_TOGGLE, ENHO, VERSIONS, VERSION_SOURCE. Server-driven objects (ABAP Platform 2025 / SAP_BASIS 8.16+, discovery-gated, return JSON metadata + AFF JSON source): DESD (CDS Logical External Schema), EVTB (RAP Event Binding), EVTO (RAP Event Object), DTSC (CDS Static Cache), CSNM (Core Schema Notation Model), COTA (Communication Target). Deprecated aliases: MESSAGES (use MSAG), FTG2 (use FEATURE_TOGGLE)."New value: +"Object type to read (on-prem): PROG, CLAS, INTF, FUNC, FUGR, INCL, DDLS, DCLS, DDLX, BDEF, SRVD, SRVB, SKTD or KTD (Knowledge Transfer Documents), TABL (transparent tables and DDIC structures), TTYP, VIEW, DOMA, DTEL, MSAG, TRAN, TABLE_CONTENTS, TABLE_QUERY, DEVC, SOBJ, SYSTEM, COMPONENTS, TEXT_ELEMENTS, VARIANTS, BSP, BSP_DEPLOY, API_STATE, INACTIVE_OBJECTS, AUTH, FEATURE_TOGGLE, ENHO, VERSIONS, VERSION_SOURCE. Server-driven objects (discovery-gated; XML metadata; source is AFF JSON, or DDL text for DTSC/DSFD/DTDC): DESD (Logical External Schema), EVTB (RAP Event Binding), EVTO (RAP Event Object), DTSC (Static Cache), CSNM (CSN Model), COTA (Communication Target), DSFD (Scalar Function Def), DTDC (Dynamic Cache), UIAD (Launchpad App Descriptor Item). Deprecated aliases: MESSAGES (use MSAG), FTG2 (use FEATURE_TOGGLE)." - changed
Input schema / properties / type / enumPrevious value: -[ - "PROG", - "CLAS", - "INTF", - "FUNC", - "FUGR", - "INCL", - "DDLS", - "DCLS", - "DDLX", - "BDEF", - "SRVD", - "SRVB", - "SKTD", - "KTD", - "TABL", - "VIEW", - "DOMA", - "DTEL", - "TRAN", - "TTYP", - "TABLE_CONTENTS", - "TABLE_QUERY", - "DEVC", - "SOBJ", - "SYSTEM", - "COMPONENTS", - "MSAG", - "MESSAGES", - "TEXT_ELEMENTS", - "VARIANTS", - "BSP", - "BSP_DEPLOY", - "API_STATE", - "INACTIVE_OBJECTS", - "AUTH", - "FEATURE_TOGGLE", - "FTG2", - "ENHO", - "VERSIONS", - "VERSION_SOURCE", - "DESD", - "DTSC", - "CSNM", - "EVTB", - "EVTO", - "COTA" -]New value: +[ + "PROG", + "CLAS", + "INTF", + "FUNC", + "FUGR", + "INCL", + "DDLS", + "DCLS", + "DDLX", + "BDEF", + "SRVD", + "SRVB", + "SKTD", + "KTD", + "TABL", + "VIEW", + "DOMA", + "DTEL", + "TRAN", + "TTYP", + "TABLE_CONTENTS", + "TABLE_QUERY", + "DEVC", + "SOBJ", + "SYSTEM", + "COMPONENTS", + "MSAG", + "MESSAGES", + "TEXT_ELEMENTS", + "VARIANTS", + "BSP", + "BSP_DEPLOY", + "API_STATE", + "INACTIVE_OBJECTS", + "AUTH", + "FEATURE_TOGGLE", + "FTG2", + "ENHO", + "VERSIONS", + "VERSION_SOURCE", + "DESD", + "DTSC", + "CSNM", + "EVTB", + "EVTO", + "COTA", + "DSFD", + "DTDC", + "UIAD" +]
- Changed
SAPSearch1 field changed- added
Input schema / additionalPropertiesAdded value: +false
- Changed
SAPTransport8 fields changed- added
Input schema / additionalPropertiesAdded value: +false - changed
Input schema / properties / action / descriptionPrevious value: -"list: show transports (defaults to current user, modifiable only). Pass summary=true for a headers-only overview that omits each transport's object lists (keeps an objectCount) — far cheaper when many transports are open. get: fetch transport details including tasks and objects. create: create a new transport request (description required). To target another system, pass target=<system | system.client | /group/> (the Transportziel / TR_TARGET, e.g. \"/TRG/\" or \"C11\"; the group and system.client forms require extended transport control to be active). Otherwise omit target and pass an optional package to let SAP infer the route (defaults to $TMP). The response reports the resolved transport target; an empty target means a LOCAL request (cannot be transported onward). release: release a single transport or task. delete: delete a transport (use recursive=true to delete tasks first; removeLockedObjects=true to strip locked objects that otherwise block deletion with \"...contains locked objects\"). remove_object: remove one object from a request, keeping the request — needs the full key pgmid+type+name. reassign: change transport owner (use recursive=true for tasks too). release_recursive: release all unreleased tasks first, then the transport itself. check: check if a transport is needed for a package/object (requires type, name, package). history: list transports referencing an object (reverse lookup; requires type, name; works without SAP_ALLOW_TRANSPORT_WRITES). layers: list the transport layers this system offers (name + description + resolved target where any) — the valid values for create's transportLayer. Use this to discover a real value instead of guessing; works without SAP_ALLOW_TRANSPORT_WRITES. Uses the package value-help endpoint (NW 7.52+); older releases report it's unavailable. targets: list the valid transport targets (Transportziel / TR_TARGET) this system offers — the valid values for create's target. Use this to discover a real target (e.g. before create with target=). Uses the official ADT target value-help; available only on releases whose ADT stack supports explicit targets (NW 7.50/7.51 report it's unavailable). Read-only."New value: +"list: show transports (defaults to current user, modifiable only). Pass summary=true for a headers-only overview that omits each transport's object lists (keeps an objectCount) — far cheaper when many transports are open. get: fetch transport details including tasks and objects. create: create a new transport request (description required). To target another system, pass target=<system | system.client | /group/> (the Transportziel / TR_TARGET, e.g. \"/TRG/\" or \"C11\"; the group and system.client forms require extended transport control to be active). Otherwise omit target and pass an optional package to let SAP infer the route (defaults to $TMP). The response reports the resolved transport target; an empty target means a LOCAL request (cannot be transported onward). release: release a single transport or task. delete: delete a transport (use recursive=true to delete tasks first; removeLockedObjects=true to strip locked objects that otherwise block deletion with \"...contains locked objects\"). remove_object: remove one object from a request, keeping the request — needs the full key pgmid+type+name. reassign: change transport owner (use recursive=true for tasks too). release_recursive: release all unreleased tasks first, then the transport itself. check: check create/modify transport needs for a package/object (requires type, name, package; operation defaults to create). history: inspect the current object lock and assignment candidates (legacy action name; not complete transport history; requires type, name; works without SAP_ALLOW_TRANSPORT_WRITES). layers: list the transport layers this system offers (name + description + resolved target where any) — the valid values for create's transportLayer. Use this to discover a real value instead of guessing; works without SAP_ALLOW_TRANSPORT_WRITES. targets: list the valid transport targets (Transportziel / TR_TARGET) this system offers — the valid values for create's target. Use this to discover a real target (e.g. before create with target=). Read-only. Both report unavailability at runtime on releases that lack the value-help endpoint." - added
Input schema / properties / maxResultsAdded value: +{ + "description": "Maximum list rows or check/history assignment candidates (defaults: list/history 50, check 10; max 1000).", + "type": "number" +} - added
Input schema / properties / operationAdded value: +{ + "description": "Check mode: create (default) or modify.", + "enum": [ + "create", + "modify" + ], + "type": "string" +} - changed
Input schema / properties / package / descriptionPrevious value: -"Package name. For create: optional — defaults to $TMP, pass an explicit package to influence the transport route (SAP infers K/W/T from the package's TADIR route). For check: required."New value: +"Package name. For create: optional — defaults to $TMP; an explicit package influences the route/target, while the request remains Workbench type K. For check: required." - changed
Input schema / properties / summary / descriptionPrevious value: -"For list only. Headers-only overview: omit each transport's (and task's) object lists, keeping id/description/owner/status/target plus an objectCount. Use it to scan many open transports cheaply, then action=\"get\" the one you want in full."New value: +"For list only. DEFAULT true: headers-only — drops each transport's (and task's) object lists, keeping id/description/owner/status/target + objectCount; use action=\"get\" for one in full. Pass false for full object lists (~5x larger)." - changed
Input schema / properties / type / descriptionPrevious value: -"Object type for check/history/remove_object actions (PROG, CLAS, DDLS, etc.). Not used by create — the SAP backend infers transport type (K/W/T) from the package's TADIR route on the CreateCorrectionRequest endpoint."New value: +"Object type for check/history/remove_object actions (PROG, CLAS, DDLS, etc.). Not used by create, which creates a Workbench (K) request." - changed
Input schema / properties / user / descriptionPrevious value: -"SAP username to filter by (for list). Defaults to the current SAP user. Use \"*\" to list all users."New value: +"SAP user for list (default: current user; \"*\" means all users)."
2 tool updates
v0.9.27- Changed
SAPContext2 fields changed- changed
Input schema / properties / action / descriptionPrevious value: -"Action:\n\"impact\" = CDS blast-radius analysis (DDLS only). USE THIS for any question like \"what breaks if I change <view>\", \"who consumes <I_*>\", \"impact analysis on <CDS>\", \"downstream of <view>\". Returns upstream AST dependencies + downstream where-used classified into RAP buckets (projectionViews, bdefs, serviceDefinitions, serviceBindings, accessControls, metadataExtensions, abapConsumers, documentation, tables, other), plus additive sibling-consistency diagnostics (consistencyHints + siblingExtensionAnalysis) when related DDLS siblings show asymmetric DDLX coverage. ALWAYS prefer over SAPQuery against DDDDLSRC/ACMDCLSRC/DDLXSRC_SRC/SRVDSRC_SRC (those text-scans produce noise this classifier filters out). Non-DDLS input returns a guardrail error.\n\"deps\" (default, can be omitted) = object understanding / forward dependency context — \"what does <object> do?\" or \"what does <object> depend on?\". Returns the object KTD when available plus public API contracts of dependencies.\n\"usages\" = reverse dependency lookup — \"who calls <object>?\". Requires cache warmup (--cache-warmup). Only \"name\" is needed. For CDS entities prefer action=\"impact\" instead.\n\"structure\" = TABL includes/appends."New value: +"Action:\n\"impact\" = CDS blast-radius analysis (DDLS only). USE THIS for any question like \"what breaks if I change <view>\", \"who consumes <I_*>\", \"impact analysis on <CDS>\", \"downstream of <view>\". Returns upstream AST dependencies + downstream where-used classified into RAP buckets (projectionViews, bdefs, serviceDefinitions, serviceBindings, accessControls, metadataExtensions, abapConsumers, documentation, tables, other), plus additive sibling-consistency diagnostics (consistencyHints + siblingExtensionAnalysis) when related DDLS siblings show asymmetric DDLX coverage. ALWAYS prefer over SAPQuery against DDDDLSRC/ACMDCLSRC/DDLXSRC_SRC/SRVDSRC_SRC (those text-scans produce noise this classifier filters out). Non-DDLS input returns a guardrail error.\n\"deps\" (default, can be omitted) = object understanding / forward dependency context — \"what does <object> do?\" or \"what does <object> depend on?\". Returns the object KTD when available plus public API contracts of dependencies.\n\"usages\" = live SAP where-used lookup. Provide \"type\" when known; without it, the name must resolve uniquely. Prefer \"impact\" for CDS.\n\"structure\" = TABL includes/appends." - changed
Input schema / properties / type / descriptionPrevious value: -"Object type. Optional for action=\"impact\" (defaults to DDLS); required otherwise."New value: +"Object type. Optional for action=\"impact\" (defaults to DDLS) or action=\"usages\"; required otherwise."
- Changed
SAPDiagnose5 fields changed- changed
Input schema / properties / action / enumPrevious value: -[ - "syntax", - "unittest", - "atc", - "cds_testcases", - "dumps", - "traces", - "trace_start", - "trace_requests", - "trace_cancel", - "system_messages", - "gateway_errors", - "object_state", - "quickfix", - "apply_quickfix", - "odata_perf", - "cds_sql", - "sql_trace_state", - "set_sql_trace_state", - "sql_trace_directory" -]New value: +[ + "syntax", + "unittest", + "atc", + "cds_testcases", + "dumps", + "traces", + "trace_start", + "trace_requests", + "trace_cancel", + "system_messages", + "gateway_errors", + "object_state", + "quickfix", + "apply_quickfix", + "odata_perf", + "cds_sql", + "sql_trace_state", + "set_sql_trace_state", + "sql_trace_directory", + "authorization_trace" +] - added
Input schema / properties / authObjectAdded value: +{ + "description": "Authorization object filter, e.g. S_TCODE.", + "type": "string" +} - changed
Input schema / properties / maxResults / descriptionPrevious value: -"Maximum results to return for dumps/system_messages/gateway_errors (default 50, bounded to a safe cap)."New value: +"Maximum results for dumps/system_messages/gateway_errors (default 50) or authorization_trace (default 100); bounded to a safe cap." - added
Input schema / properties / onlyFailuresAdded value: +{ + "description": "For authorization_trace: return only denied checks (RC<>0), similar to the SU53 failure view.", + "type": "boolean" +} - changed
Input schema / properties / user / descriptionPrevious value: -"Filter dumps by SAP user (for dumps action)"New value: +"SAP-user filter for dumps, feeds, or authorization_trace."
4 tool updates
v0.9.23- Changed
SAPContext4 fields changed- changed
Input schema / properties / action / descriptionPrevious value: -"Action:\n\"impact\" = CDS blast-radius analysis (DDLS only). USE THIS for any question like \"what breaks if I change <view>\", \"who consumes <I_*>\", \"impact analysis on <CDS>\", \"downstream of <view>\". Returns upstream AST dependencies + downstream where-used classified into RAP buckets (projectionViews, bdefs, serviceDefinitions, serviceBindings, accessControls, metadataExtensions, abapConsumers, documentation, tables, other), plus additive sibling-consistency diagnostics (consistencyHints + siblingExtensionAnalysis) when related DDLS siblings show asymmetric DDLX coverage. ALWAYS prefer over SAPQuery against DDDDLSRC/ACMDCLSRC/DDLXSRC_SRC/SRVDSRC_SRC (those text-scans produce noise this classifier filters out). Non-DDLS input returns a guardrail error.\n\"deps\" (default, can be omitted) = object understanding / forward dependency context — \"what does <object> do?\" or \"what does <object> depend on?\". Returns the object KTD when available plus public API contracts of dependencies.\n\"usages\" = reverse dependency lookup — \"who calls <object>?\". Requires cache warmup (--cache-warmup). Only \"name\" is needed. For CDS entities prefer action=\"impact\" instead."New value: +"Action:\n\"impact\" = CDS blast-radius analysis (DDLS only). USE THIS for any question like \"what breaks if I change <view>\", \"who consumes <I_*>\", \"impact analysis on <CDS>\", \"downstream of <view>\". Returns upstream AST dependencies + downstream where-used classified into RAP buckets (projectionViews, bdefs, serviceDefinitions, serviceBindings, accessControls, metadataExtensions, abapConsumers, documentation, tables, other), plus additive sibling-consistency diagnostics (consistencyHints + siblingExtensionAnalysis) when related DDLS siblings show asymmetric DDLX coverage. ALWAYS prefer over SAPQuery against DDDDLSRC/ACMDCLSRC/DDLXSRC_SRC/SRVDSRC_SRC (those text-scans produce noise this classifier filters out). Non-DDLS input returns a guardrail error.\n\"deps\" (default, can be omitted) = object understanding / forward dependency context — \"what does <object> do?\" or \"what does <object> depend on?\". Returns the object KTD when available plus public API contracts of dependencies.\n\"usages\" = reverse dependency lookup — \"who calls <object>?\". Requires cache warmup (--cache-warmup). Only \"name\" is needed. For CDS entities prefer action=\"impact\" instead.\n\"structure\" = TABL includes/appends." - changed
Input schema / properties / action / enumPrevious value: -[ - "impact", - "deps", - "usages" -]New value: +[ + "impact", + "deps", + "usages", + "structure" +] - changed
Input schema / properties / type / descriptionPrevious value: -"Object type. Required for action=\"deps\" and action=\"usages\". Optional for action=\"impact\" — defaults to DDLS (the only supported type for impact)."New value: +"Object type. Optional for action=\"impact\" (defaults to DDLS); required otherwise." - changed
Input schema / properties / type / enumPrevious value: -[ - "CLAS", - "INTF", - "PROG", - "FUNC", - "DDLS" -]New value: +[ + "CLAS", + "INTF", + "PROG", + "FUNC", + "DDLS", + "TABL" +]
- Changed
SAPDiagnose1 field changed- changed
Input schema / properties / url / descriptionPrevious value: -"For action=\"odata_perf\": the host-relative OData path to probe, copied from the Fiori app's Network tab (e.g. \"/sap/opu/odata4/sap/.../Entity?$filter=...\" or \"/sap/opu/odata/sap/<SRV>/<EntitySet>?$top=20\"). Must be a path on the SAP system ARC-1 connects to — absolute URLs are rejected."New value: +"For odata_perf: the host-relative OData path to probe, from the Fiori app's Network tab (e.g. \"/sap/opu/odata4/sap/.../Entity?$filter=…\"). Must be a path on the connected system — absolute URLs are rejected."
- Changed
SAPManage4 fields changed- changed
Input schema / properties / domainId / descriptionPrevious value: -"Domain ID for FLP catalog creation (e.g., ZARC1_SALES)."New value: +"Domain ID — required for flp_create_catalog (e.g., ZARC1_SALES)." - added
Input schema / properties / responsibleAdded value: +{ + "description": "BTP only: the internal ABAP user (XUBNAME, e.g. CB9980000000) for the new package person-responsible. Auto-resolved from prior object creates if omitted; the IAS email is rejected.", + "type": "string" +} - changed
Input schema / properties / softwareComponent / descriptionPrevious value: -"Software component for create_package (default: LOCAL)."New value: +"Software component for create_package (default: LOCAL on-prem, ZLOCAL on BTP)." - changed
Input schema / properties / title / descriptionPrevious value: -"Title for FLP catalog/group creation."New value: +"Title — required for flp_create_catalog and flp_create_group."
- Changed
SAPRead2 fields changed- added
Input schema / properties / fromLabelAdded value: +{ + "description": "action=\"diff\" optional display label for the OLD side in the summary and patch header, e.g. \"DNT-6-6: Validate discounts (DS7K900123)\". Does not affect source resolution.", + "type": "string" +} - added
Input schema / properties / toLabelAdded value: +{ + "description": "action=\"diff\" optional display label for the NEW side in the summary and patch header, e.g. \"active\" or \"inactive draft\". Does not affect source resolution.", + "type": "string" +}
3 tool updates
v0.9.21- Changed
SAPDiagnose14 fields changed- changed
Input schema / properties / action / enumPrevious value: -[ - "syntax", - "unittest", - "atc", - "cds_testcases", - "dumps", - "traces", - "system_messages", - "gateway_errors", - "object_state", - "quickfix", - "apply_quickfix" -]New value: +[ + "syntax", + "unittest", + "atc", + "cds_testcases", + "dumps", + "traces", + "trace_start", + "trace_requests", + "trace_cancel", + "system_messages", + "gateway_errors", + "object_state", + "quickfix", + "apply_quickfix", + "odata_perf", + "cds_sql", + "sql_trace_state", + "set_sql_trace_state", + "sql_trace_directory" +] - added
Input schema / properties / aggregateAdded value: +{ + "description": "For trace_start: aggregate the trace (default true).", + "type": "boolean" +} - added
Input schema / properties / coverageAdded value: +{ + "description": "For action=\"unittest\": also return statement/branch/procedure coverage for the object, plus methodsBelowFull — the methods below 100% statement coverage, worst first (what to test next) — in one extra round-trip. If the coverage endpoint or measurement is unavailable, returns the tests without coverage. Default false.", + "type": "boolean" +} - added
Input schema / properties / descriptionAdded value: +{ + "description": "For trace_start: optional label for the trace request.", + "type": "string" +} - added
Input schema / properties / expiresHoursAdded value: +{ + "description": "For trace_start: hours until the armed request auto-expires (default 24).", + "type": "number" +} - changed
Input schema / properties / id / descriptionPrevious value: -"Dump or trace ID (for dumps/traces actions). Omit to list, provide to get details."New value: +"Dump or trace ID (for dumps/traces actions); also the trace-request id to cancel (for trace_cancel). Omit to list, provide to get details." - added
Input schema / properties / maxExecutionsAdded value: +{ + "description": "For trace_start: how many matching executions to capture before the request is consumed (default 1).", + "type": "number" +} - changed
Input schema / properties / name / descriptionPrevious value: -"Object name (for syntax/unittest/atc/object_state); the CDS entity / DDLS source name for cds_testcases"New value: +"Object name (for syntax/unittest/atc/object_state); the CDS entity / DDLS source name for cds_testcases and cds_sql" - added
Input schema / properties / objectTypeAdded value: +{ + "description": "For trace_start: what to match within the process. Defaults to the valid type for the process type (http→url, dialog→transaction, batch→report, rfc→functionModule).", + "enum": [ + "any", + "url", + "transaction", + "report", + "functionModule" + ], + "type": "string" +} - added
Input schema / properties / processTypeAdded value: +{ + "description": "For trace_start: the kind of work process to capture. Default \"http\" (OData/Gateway). dialog = SAP GUI transaction, batch = background job, rfc = RFC call.", + "enum": [ + "any", + "http", + "dialog", + "batch", + "rfc" + ], + "type": "string" +} - added
Input schema / properties / sqlOnAdded value: +{ + "description": "For action=\"set_sql_trace_state\": true to arm the ST05 SQL trace, false to disarm. Combine with user to filter the trace to one SAP user.", + "type": "boolean" +} - added
Input schema / properties / sqlTraceAdded value: +{ + "description": "For trace_start: capture SQL/DB accesses (default true — required for analysis=\"dbAccesses\").", + "type": "boolean" +} - added
Input schema / properties / traceUserAdded value: +{ + "description": "For trace_start/trace_requests: the SAP user whose matching execution is traced/listed. Defaults to the connected user.", + "type": "string" +} - added
Input schema / properties / urlAdded value: +{ + "description": "For action=\"odata_perf\": the host-relative OData path to probe, copied from the Fiori app's Network tab (e.g. \"/sap/opu/odata4/sap/.../Entity?$filter=...\" or \"/sap/opu/odata/sap/<SRV>/<EntitySet>?$top=20\"). Must be a path on the SAP system ARC-1 connects to — absolute URLs are rejected.", + "type": "string" +}
- Changed
SAPManage4 fields changed- added
Input schema / properties / apiStateAdded value: +{ + "description": "For set_api_state: target state of the object's API release contract — RELEASED (mark released for ABAP Cloud / Clean Core) or NOT_RELEASED (revoke). Default RELEASED. Visibility (ABAP Cloud / Key User Apps) follows the contract's defaults. Read the current state first with SAPRead(type=\"API_STATE\").", + "enum": [ + "RELEASED", + "NOT_RELEASED" + ], + "type": "string" +} - added
Input schema / properties / contractAdded value: +{ + "description": "For set_api_state: which release contract to set. Default C1 (Key-User/Cloud — the common clean-core contract). Object types support different contracts: e.g. service definitions (SRVD) only support C0, classic DDIC views only C3, behavior definitions and tables support C0+C1. If the object does not support the chosen contract, the error lists the ones it does.", + "enum": [ + "C0", + "C1", + "C2", + "C3", + "C4" + ], + "type": "string" +} - changed
Input schema / properties / objectType / descriptionPrevious value: -"ADT object type (e.g., CLAS/OC, DDLS/DF, PROG/P). Required for change_package."New value: +"ADT object type (e.g., CLAS/OC, DDLS/DF, PROG/P). Required for change_package. For set_api_state: object type of \"name\" when objectUri is omitted (e.g. CLAS, INTF, DDLS, TABL)." - changed
Input schema / properties / objectUri / descriptionPrevious value: -"ADT URI of the object to move (e.g., /sap/bc/adt/oo/classes/zcl_my_class). If not provided, resolved automatically from objectName + objectType via search."New value: +"ADT URI of the object to move (e.g., /sap/bc/adt/oo/classes/zcl_my_class). If not provided, resolved automatically from objectName + objectType via search. For set_api_state: the object whose API release contract to set (or pass name + objectType instead)."
- Changed
SAPRead1 field changed- changed
Input schema / properties / type / enumPrevious value: -[ - "PROG", - "CLAS", - "INTF", - "FUNC", - "FUGR", - "INCL", - "DDLS", - "DCLS", - "DDLX", - "BDEF", - "SRVD", - "SRVB", - "SKTD", - "KTD", - "TABL", - "VIEW", - "DOMA", - "DTEL", - "TRAN", - "TABLE_CONTENTS", - "TABLE_QUERY", - "DEVC", - "SOBJ", - "SYSTEM", - "COMPONENTS", - "MSAG", - "MESSAGES", - "TEXT_ELEMENTS", - "VARIANTS", - "BSP", - "BSP_DEPLOY", - "API_STATE", - "INACTIVE_OBJECTS", - "AUTH", - "FEATURE_TOGGLE", - "FTG2", - "ENHO", - "VERSIONS", - "VERSION_SOURCE", - "DESD", - "DTSC", - "CSNM", - "EVTB", - "EVTO", - "COTA" -]New value: +[ + "PROG", + "CLAS", + "INTF", + "FUNC", + "FUGR", + "INCL", + "DDLS", + "DCLS", + "DDLX", + "BDEF", + "SRVD", + "SRVB", + "SKTD", + "KTD", + "TABL", + "VIEW", + "DOMA", + "DTEL", + "TRAN", + "TTYP", + "TABLE_CONTENTS", + "TABLE_QUERY", + "DEVC", + "SOBJ", + "SYSTEM", + "COMPONENTS", + "MSAG", + "MESSAGES", + "TEXT_ELEMENTS", + "VARIANTS", + "BSP", + "BSP_DEPLOY", + "API_STATE", + "INACTIVE_OBJECTS", + "AUTH", + "FEATURE_TOGGLE", + "FTG2", + "ENHO", + "VERSIONS", + "VERSION_SOURCE", + "DESD", + "DTSC", + "CSNM", + "EVTB", + "EVTO", + "COTA" +]
2 tool updates
v0.9.20- Changed
SAPContext2 fields changed- changed
Input schema / properties / action / descriptionPrevious value: -"Action:\n\"impact\" = CDS blast-radius analysis (DDLS only). USE THIS for any question like \"what breaks if I change <view>\", \"who consumes <I_*>\", \"impact analysis on <CDS>\", \"downstream of <view>\". Returns upstream AST dependencies + downstream where-used classified into RAP buckets (projectionViews, bdefs, serviceDefinitions, serviceBindings, accessControls, metadataExtensions, abapConsumers, documentation, tables, other), plus additive sibling-consistency diagnostics (consistencyHints + siblingExtensionAnalysis) when related DDLS siblings show asymmetric DDLX coverage. ALWAYS prefer over SAPQuery against DDDDLSRC/ACMDCLSRC/DDLXSRC_SRC/SRVDSRC_SRC (those text-scans produce noise this classifier filters out). Non-DDLS input returns a guardrail error.\n\"deps\" (default, can be omitted) = forward dependency context — \"what does <object> depend on?\". Returns public API contracts of dependencies.\n\"usages\" = reverse dependency lookup — \"who calls <object>?\". Requires cache warmup (--cache-warmup). Only \"name\" is needed. For CDS entities prefer action=\"impact\" instead."New value: +"Action:\n\"impact\" = CDS blast-radius analysis (DDLS only). USE THIS for any question like \"what breaks if I change <view>\", \"who consumes <I_*>\", \"impact analysis on <CDS>\", \"downstream of <view>\". Returns upstream AST dependencies + downstream where-used classified into RAP buckets (projectionViews, bdefs, serviceDefinitions, serviceBindings, accessControls, metadataExtensions, abapConsumers, documentation, tables, other), plus additive sibling-consistency diagnostics (consistencyHints + siblingExtensionAnalysis) when related DDLS siblings show asymmetric DDLX coverage. ALWAYS prefer over SAPQuery against DDDDLSRC/ACMDCLSRC/DDLXSRC_SRC/SRVDSRC_SRC (those text-scans produce noise this classifier filters out). Non-DDLS input returns a guardrail error.\n\"deps\" (default, can be omitted) = object understanding / forward dependency context — \"what does <object> do?\" or \"what does <object> depend on?\". Returns the object KTD when available plus public API contracts of dependencies.\n\"usages\" = reverse dependency lookup — \"who calls <object>?\". Requires cache warmup (--cache-warmup). Only \"name\" is needed. For CDS entities prefer action=\"impact\" instead." - added
Input schema / properties / includeKtdAdded value: +{ + "description": "Only for action=\"deps\". When true/default, prepend the object Knowledge Transfer Document (KTD/SKTD) when one exists. Set false to skip the KTD lookup.", + "type": "boolean" +}
- Changed
SAPRead3 fields changed- changed
Input schema / properties / grep / descriptionPrevious value: -"Regex pattern (case-insensitive) to search within the object source. Returns only matching lines with 1-based line numbers and ±3 context lines, instead of the full source — token-efficient. For CLAS, matches are annotated with the owning class/method; combine with include= to scope a section, but do NOT combine with method= (use grep to find, then method= to read). Works for source-bearing types (CLAS, INTF, DDLS, DCLS, BDEF, SRVD, SRVB, SKTD, DDLX, TABL, PROG, FUNC, FUGR, INCL, VIEW). Falls back to a literal search when the pattern is not valid regex."New value: +"Regex pattern (case-insensitive) to search within the object source. Returns only matching lines with 1-based line numbers and ±3 context lines, instead of the full source — token-efficient. For CLAS, matches are annotated with the owning class/method; combine with include= to scope a section, but do NOT combine with method= (use grep to find, then method= to read). Works for source-bearing types (CLAS, INTF, DDLS, DCLS, BDEF, SRVD, SRVB, SKTD/KTD, DDLX, TABL, PROG, FUNC, FUGR, INCL, VIEW). Falls back to a literal search when the pattern is not valid regex." - changed
Input schema / properties / type / descriptionPrevious value: -"Object type to read (on-prem): PROG, CLAS, INTF, FUNC, FUGR, INCL, DDLS, DCLS, DDLX, BDEF, SRVD, SRVB, SKTD, TABL (transparent tables and DDIC structures), VIEW, DOMA, DTEL, MSAG, TRAN, TABLE_CONTENTS, TABLE_QUERY, DEVC, SOBJ, SYSTEM, COMPONENTS, TEXT_ELEMENTS, VARIANTS, BSP, BSP_DEPLOY, API_STATE, INACTIVE_OBJECTS, AUTH, FEATURE_TOGGLE, ENHO, VERSIONS, VERSION_SOURCE. Server-driven objects (ABAP Platform 2025 / SAP_BASIS 8.16+, discovery-gated, return JSON metadata + AFF JSON source): DESD (CDS Logical External Schema), EVTB (RAP Event Binding), EVTO (RAP Event Object), DTSC (CDS Static Cache), CSNM (Core Schema Notation Model), COTA (Communication Target). Deprecated aliases: MESSAGES (use MSAG), FTG2 (use FEATURE_TOGGLE)."New value: +"Object type to read (on-prem): PROG, CLAS, INTF, FUNC, FUGR, INCL, DDLS, DCLS, DDLX, BDEF, SRVD, SRVB, SKTD or KTD (Knowledge Transfer Documents), TABL (transparent tables and DDIC structures), VIEW, DOMA, DTEL, MSAG, TRAN, TABLE_CONTENTS, TABLE_QUERY, DEVC, SOBJ, SYSTEM, COMPONENTS, TEXT_ELEMENTS, VARIANTS, BSP, BSP_DEPLOY, API_STATE, INACTIVE_OBJECTS, AUTH, FEATURE_TOGGLE, ENHO, VERSIONS, VERSION_SOURCE. Server-driven objects (ABAP Platform 2025 / SAP_BASIS 8.16+, discovery-gated, return JSON metadata + AFF JSON source): DESD (CDS Logical External Schema), EVTB (RAP Event Binding), EVTO (RAP Event Object), DTSC (CDS Static Cache), CSNM (Core Schema Notation Model), COTA (Communication Target). Deprecated aliases: MESSAGES (use MSAG), FTG2 (use FEATURE_TOGGLE)." - changed
Input schema / properties / type / enumPrevious value: -[ - "PROG", - "CLAS", - "INTF", - "FUNC", - "FUGR", - "INCL", - "DDLS", - "DCLS", - "DDLX", - "BDEF", - "SRVD", - "SRVB", - "SKTD", - "TABL", - "VIEW", - "DOMA", - "DTEL", - "TRAN", - "TABLE_CONTENTS", - "TABLE_QUERY", - "DEVC", - "SOBJ", - "SYSTEM", - "COMPONENTS", - "MSAG", - "MESSAGES", - "TEXT_ELEMENTS", - "VARIANTS", - "BSP", - "BSP_DEPLOY", - "API_STATE", - "INACTIVE_OBJECTS", - "AUTH", - "FEATURE_TOGGLE", - "FTG2", - "ENHO", - "VERSIONS", - "VERSION_SOURCE", - "DESD", - "DTSC", - "CSNM", - "EVTB", - "EVTO", - "COTA" -]New value: +[ + "PROG", + "CLAS", + "INTF", + "FUNC", + "FUGR", + "INCL", + "DDLS", + "DCLS", + "DDLX", + "BDEF", + "SRVD", + "SRVB", + "SKTD", + "KTD", + "TABL", + "VIEW", + "DOMA", + "DTEL", + "TRAN", + "TABLE_CONTENTS", + "TABLE_QUERY", + "DEVC", + "SOBJ", + "SYSTEM", + "COMPONENTS", + "MSAG", + "MESSAGES", + "TEXT_ELEMENTS", + "VARIANTS", + "BSP", + "BSP_DEPLOY", + "API_STATE", + "INACTIVE_OBJECTS", + "AUTH", + "FEATURE_TOGGLE", + "FTG2", + "ENHO", + "VERSIONS", + "VERSION_SOURCE", + "DESD", + "DTSC", + "CSNM", + "EVTB", + "EVTO", + "COTA" +]
2 tool updates
v0.9.18- Changed
SAPRead3 fields changed- added
Input schema / properties / actionAdded value: +{ + "description": "Set to \"diff\" for a unified diff between two source versions (uses from/to) — cheaper than fetching both sources. Source types only: PROG, CLAS, INTF, FUNC, FUGR, INCL, DDLS, DCLS, BDEF, SRVD, DDLX, TABL.", + "enum": [ + "diff" + ], + "type": "string" +} - added
Input schema / properties / fromAdded value: +{ + "description": "action=\"diff\" OLD side: \"active\" (default), \"inactive\", a revision id from SAPRead(type=\"VERSIONS\"), or a /sap/bc/adt/ revision URI.", + "type": "string" +} - added
Input schema / properties / toAdded value: +{ + "description": "action=\"diff\" NEW side (default \"inactive\" = pending unactivated changes). Same values as from.", + "type": "string" +}
- Changed
SAPTransport6 fields changed- changed
Input schema / properties / action / descriptionPrevious value: -"list: show transports (defaults to current user, modifiable only). get: fetch transport details including tasks and objects. create: create a new transport request (description required). To target another system, pass target=<system | system.client | /group/> (the Transportziel / TR_TARGET, e.g. \"/TRG/\" or \"C11\"; the group and system.client forms require extended transport control to be active). Otherwise omit target and pass an optional package to let SAP infer the route (defaults to $TMP). The response reports the resolved transport target; an empty target means a LOCAL request (cannot be transported onward). release: release a single transport or task. delete: delete a transport (use recursive=true to delete tasks first; removeLockedObjects=true to strip locked objects that otherwise block deletion with \"...contains locked objects\"). reassign: change transport owner (use recursive=true for tasks too). release_recursive: release all unreleased tasks first, then the transport itself. check: check if a transport is needed for a package/object (requires type, name, package). history: list transports referencing an object (reverse lookup; requires type, name; works without SAP_ALLOW_TRANSPORT_WRITES). layers: list the transport layers this system offers (name + description + resolved target where any) — the valid values for create's transportLayer. Use this to discover a real value instead of guessing; works without SAP_ALLOW_TRANSPORT_WRITES. Uses the package value-help endpoint (NW 7.52+); older releases report it's unavailable. targets: list the valid transport targets (Transportziel / TR_TARGET) this system offers — the valid values for create's target. Use this to discover a real target (e.g. before create with target=). Uses the official ADT target value-help; available only on releases whose ADT stack supports explicit targets (NW 7.50/7.51 report it's unavailable). Read-only."New value: +"list: show transports (defaults to current user, modifiable only). Pass summary=true for a headers-only overview that omits each transport's object lists (keeps an objectCount) — far cheaper when many transports are open. get: fetch transport details including tasks and objects. create: create a new transport request (description required). To target another system, pass target=<system | system.client | /group/> (the Transportziel / TR_TARGET, e.g. \"/TRG/\" or \"C11\"; the group and system.client forms require extended transport control to be active). Otherwise omit target and pass an optional package to let SAP infer the route (defaults to $TMP). The response reports the resolved transport target; an empty target means a LOCAL request (cannot be transported onward). release: release a single transport or task. delete: delete a transport (use recursive=true to delete tasks first; removeLockedObjects=true to strip locked objects that otherwise block deletion with \"...contains locked objects\"). remove_object: remove one object from a request, keeping the request — needs the full key pgmid+type+name. reassign: change transport owner (use recursive=true for tasks too). release_recursive: release all unreleased tasks first, then the transport itself. check: check if a transport is needed for a package/object (requires type, name, package). history: list transports referencing an object (reverse lookup; requires type, name; works without SAP_ALLOW_TRANSPORT_WRITES). layers: list the transport layers this system offers (name + description + resolved target where any) — the valid values for create's transportLayer. Use this to discover a real value instead of guessing; works without SAP_ALLOW_TRANSPORT_WRITES. Uses the package value-help endpoint (NW 7.52+); older releases report it's unavailable. targets: list the valid transport targets (Transportziel / TR_TARGET) this system offers — the valid values for create's target. Use this to discover a real target (e.g. before create with target=). Uses the official ADT target value-help; available only on releases whose ADT stack supports explicit targets (NW 7.50/7.51 report it's unavailable). Read-only." - changed
Input schema / properties / id / descriptionPrevious value: -"Transport request ID, e.g. A4HK900123 (required for get/release/delete/reassign/release_recursive)"New value: +"Transport request ID, e.g. A4HK900123 (required for get/release/delete/reassign/release_recursive/remove_object)" - changed
Input schema / properties / name / descriptionPrevious value: -"Object name (for check or history actions)"New value: +"Object name (for check, history, or remove_object actions)" - added
Input schema / properties / pgmidAdded value: +{ + "description": "Program ID for remove_object: \"R3TR\" (whole object) or \"LIMU\" (sub-object). Required — object type alone does not determine pgmid.", + "type": "string" +} - added
Input schema / properties / summaryAdded value: +{ + "description": "For list only. Headers-only overview: omit each transport's (and task's) object lists, keeping id/description/owner/status/target plus an objectCount. Use it to scan many open transports cheaply, then action=\"get\" the one you want in full.", + "type": "boolean" +} - changed
Input schema / properties / type / descriptionPrevious value: -"Object type for check/history actions (PROG, CLAS, DDLS, etc.). Not used by create — the SAP backend infers transport type (K/W/T) from the package's TADIR route on the CreateCorrectionRequest endpoint."New value: +"Object type for check/history/remove_object actions (PROG, CLAS, DDLS, etc.). Not used by create — the SAP backend infers transport type (K/W/T) from the package's TADIR route on the CreateCorrectionRequest endpoint."
1 tool update
v0.9.14- Changed
SAPRead1 field changed- added
Input schema / properties / grep / maxLengthAdded value: +512
4 tool updates
v0.9.13- Changed
SAPDiagnose2 fields changed- changed
Input schema / properties / action / enumPrevious value: -[ - "syntax", - "unittest", - "atc", - "dumps", - "traces", - "system_messages", - "gateway_errors", - "object_state", - "quickfix", - "apply_quickfix" -]New value: +[ + "syntax", + "unittest", + "atc", + "cds_testcases", + "dumps", + "traces", + "system_messages", + "gateway_errors", + "object_state", + "quickfix", + "apply_quickfix" +] - changed
Input schema / properties / name / descriptionPrevious value: -"Object name (for syntax/unittest/atc/object_state)"New value: +"Object name (for syntax/unittest/atc/object_state); the CDS entity / DDLS source name for cds_testcases"
- Changed
SAPManage1 field changed- added
Input schema / properties / recordChangesAdded value: +{ + "description": "Whether the created package records object changes in transport requests. Defaults to true for non-LOCAL software components or when a transport layer is set; false for literal LOCAL packages.", + "type": "boolean" +}
- Changed
SAPRead4 fields changed- changed
Input schema / properties / expand_includes / descriptionPrevious value: -"For FUGR type only. When true, expands all INCLUDE statements and returns the full source of each include inline."New value: +"For FUGR type only. When true, recursively expands the function group include tree — the main source plus all nested INCLUDEs (the FUNCTION...ENDFUNCTION bodies live in nested LZ<grp>U01/U02 includes, so a flat one-level walk misses them). Each block is prefixed with a \"=== name ===\" marker; depth/count-capped. Dynpros and GUI status are not included (ADT does not expose them over REST)." - changed
Input schema / properties / grep / descriptionPrevious value: -"Regex pattern (case-insensitive) to search within the object source. Returns only matching lines with 1-based line numbers and ±3 context lines, instead of the full source — token-efficient. For CLAS, matches are annotated with the owning class/method; combine with include= to scope a section, but do NOT combine with method= (use grep to find, then method= to read). Works for source-bearing types (CLAS, INTF, DDLS, DCLS, BDEF, SRVD, DDLX, TABL, PROG, FUNC, INCL, VIEW). Falls back to a literal search when the pattern is not valid regex."New value: +"Regex pattern (case-insensitive) to search within the object source. Returns only matching lines with 1-based line numbers and ±3 context lines, instead of the full source — token-efficient. For CLAS, matches are annotated with the owning class/method; combine with include= to scope a section, but do NOT combine with method= (use grep to find, then method= to read). Works for source-bearing types (CLAS, INTF, DDLS, DCLS, BDEF, SRVD, SRVB, SKTD, DDLX, TABL, PROG, FUNC, FUGR, INCL, VIEW). Falls back to a literal search when the pattern is not valid regex." - changed
Input schema / properties / type / descriptionPrevious value: -"Object type to read (on-prem): PROG, CLAS, INTF, FUNC, FUGR, INCL, DDLS, DCLS, DDLX, BDEF, SRVD, SRVB, SKTD, TABL (transparent tables and DDIC structures), VIEW, DOMA, DTEL, MSAG, TRAN, TABLE_CONTENTS, TABLE_QUERY, DEVC, SOBJ, SYSTEM, COMPONENTS, TEXT_ELEMENTS, VARIANTS, BSP, BSP_DEPLOY, API_STATE, INACTIVE_OBJECTS, AUTH, FEATURE_TOGGLE, ENHO, VERSIONS, VERSION_SOURCE. Deprecated aliases: MESSAGES (use MSAG), FTG2 (use FEATURE_TOGGLE)."New value: +"Object type to read (on-prem): PROG, CLAS, INTF, FUNC, FUGR, INCL, DDLS, DCLS, DDLX, BDEF, SRVD, SRVB, SKTD, TABL (transparent tables and DDIC structures), VIEW, DOMA, DTEL, MSAG, TRAN, TABLE_CONTENTS, TABLE_QUERY, DEVC, SOBJ, SYSTEM, COMPONENTS, TEXT_ELEMENTS, VARIANTS, BSP, BSP_DEPLOY, API_STATE, INACTIVE_OBJECTS, AUTH, FEATURE_TOGGLE, ENHO, VERSIONS, VERSION_SOURCE. Server-driven objects (ABAP Platform 2025 / SAP_BASIS 8.16+, discovery-gated, return JSON metadata + AFF JSON source): DESD (CDS Logical External Schema), EVTB (RAP Event Binding), EVTO (RAP Event Object), DTSC (CDS Static Cache), CSNM (Core Schema Notation Model), COTA (Communication Target). Deprecated aliases: MESSAGES (use MSAG), FTG2 (use FEATURE_TOGGLE)." - changed
Input schema / properties / type / enumPrevious value: -[ - "PROG", - "CLAS", - "INTF", - "FUNC", - "FUGR", - "INCL", - "DDLS", - "DCLS", - "DDLX", - "BDEF", - "SRVD", - "SRVB", - "SKTD", - "TABL", - "VIEW", - "DOMA", - "DTEL", - "TRAN", - "TABLE_CONTENTS", - "TABLE_QUERY", - "DEVC", - "SOBJ", - "SYSTEM", - "COMPONENTS", - "MSAG", - "MESSAGES", - "TEXT_ELEMENTS", - "VARIANTS", - "BSP", - "BSP_DEPLOY", - "API_STATE", - "INACTIVE_OBJECTS", - "AUTH", - "FEATURE_TOGGLE", - "FTG2", - "ENHO", - "VERSIONS", - "VERSION_SOURCE" -]New value: +[ + "PROG", + "CLAS", + "INTF", + "FUNC", + "FUGR", + "INCL", + "DDLS", + "DCLS", + "DDLX", + "BDEF", + "SRVD", + "SRVB", + "SKTD", + "TABL", + "VIEW", + "DOMA", + "DTEL", + "TRAN", + "TABLE_CONTENTS", + "TABLE_QUERY", + "DEVC", + "SOBJ", + "SYSTEM", + "COMPONENTS", + "MSAG", + "MESSAGES", + "TEXT_ELEMENTS", + "VARIANTS", + "BSP", + "BSP_DEPLOY", + "API_STATE", + "INACTIVE_OBJECTS", + "AUTH", + "FEATURE_TOGGLE", + "FTG2", + "ENHO", + "VERSIONS", + "VERSION_SOURCE", + "DESD", + "DTSC", + "CSNM", + "EVTB", + "EVTO", + "COTA" +]
- Changed
SAPTransport5 fields changed- changed
Input schema / properties / action / descriptionPrevious value: -"list: show transports (defaults to current user, modifiable only). get: fetch transport details including tasks and objects. create: create a new transport request (description required; package optional, defaults to $TMP — pass an explicit package to influence the transport route/type). release: release a single transport or task. delete: delete a transport (use recursive=true to delete tasks first). reassign: change transport owner (use recursive=true for tasks too). release_recursive: release all unreleased tasks first, then the transport itself. check: check if a transport is needed for a package/object (requires type, name, package). history: list transports referencing an object (reverse lookup; requires type, name; works without SAP_ALLOW_TRANSPORT_WRITES)."New value: +"list: show transports (defaults to current user, modifiable only). get: fetch transport details including tasks and objects. create: create a new transport request (description required). To target another system, pass target=<system | system.client | /group/> (the Transportziel / TR_TARGET, e.g. \"/TRG/\" or \"C11\"; the group and system.client forms require extended transport control to be active). Otherwise omit target and pass an optional package to let SAP infer the route (defaults to $TMP). The response reports the resolved transport target; an empty target means a LOCAL request (cannot be transported onward). release: release a single transport or task. delete: delete a transport (use recursive=true to delete tasks first; removeLockedObjects=true to strip locked objects that otherwise block deletion with \"...contains locked objects\"). reassign: change transport owner (use recursive=true for tasks too). release_recursive: release all unreleased tasks first, then the transport itself. check: check if a transport is needed for a package/object (requires type, name, package). history: list transports referencing an object (reverse lookup; requires type, name; works without SAP_ALLOW_TRANSPORT_WRITES). layers: list the transport layers this system offers (name + description + resolved target where any) — the valid values for create's transportLayer. Use this to discover a real value instead of guessing; works without SAP_ALLOW_TRANSPORT_WRITES. Uses the package value-help endpoint (NW 7.52+); older releases report it's unavailable. targets: list the valid transport targets (Transportziel / TR_TARGET) this system offers — the valid values for create's target. Use this to discover a real target (e.g. before create with target=). Uses the official ADT target value-help; available only on releases whose ADT stack supports explicit targets (NW 7.50/7.51 report it's unavailable). Read-only." - changed
Input schema / properties / action / enumPrevious value: -[ - "list", - "get", - "check", - "history" -]New value: +[ + "list", + "get", + "check", + "history", + "layers", + "targets" +] - added
Input schema / properties / removeLockedObjectsAdded value: +{ + "description": "For delete only. Strip locked objects from each task before deleting, so a request that still holds a locked object (e.g. a deleted object's lingering record → HTTP 400 \"...contains locked objects\") can be removed.", + "type": "boolean" +} - added
Input schema / properties / targetAdded value: +{ + "description": "Explicit transport target (Transportziel / TR_TARGET) for create — what the user means by \"create a transport with target X\". Forms: a system (\"C11\"), system.client (\"C11.021\"), or target group (\"/TRG/\"). The group and system.client forms require extended transport control (CTC) to be active. Created via the tm:root/newrequest endpoint (the only ADT path that sets the target directly) — this needs a newer ABAP Platform / S/4HANA; SAP_BASIS 7.50 rejects it with \"user action is not supported\" (an ADT-stack limitation, so set the target in SE09/SE10 there instead). SAP validates the target — an unknown target is rejected. Pass the exact value the user gives; do not invent one.", + "type": "string" +} - added
Input schema / properties / transportLayerAdded value: +{ + "description": "Transport layer for create (optional, advanced). Sent as the ?transportLayer= query param to override which consolidation route — and therefore which target — SAP resolves. OMIT IT by default: SAP resolves the target from the package automatically, which is correct for almost all cases. Never invent a value — if you need a specific layer, obtain it from action=\"layers\" or from the user. Only effective when that layer has a classic STMS consolidation route; otherwise the request is local regardless.", + "type": "string" +}
1 tool update
v0.9.7- Changed
SAPRead6 fields changed- added
Input schema / properties / columnsAdded value: +{ + "description": "For TABLE_QUERY: columns to SELECT (default: all). Example: [\"MATNR\",\"BWART\",\"BUDAT\",\"MENGE\"].", + "items": { + "type": "string" + }, + "type": "array" +} - added
Input schema / properties / grepAdded value: +{ + "description": "Regex pattern (case-insensitive) to search within the object source. Returns only matching lines with 1-based line numbers and ±3 context lines, instead of the full source — token-efficient. For CLAS, matches are annotated with the owning class/method; combine with include= to scope a section, but do NOT combine with method= (use grep to find, then method= to read). Works for source-bearing types (CLAS, INTF, DDLS, DCLS, BDEF, SRVD, DDLX, TABL, PROG, FUNC, INCL, VIEW). Falls back to a literal search when the pattern is not valid regex.", + "type": "string" +} - changed
Input schema / properties / maxRows / descriptionPrevious value: -"For TABLE_CONTENTS: max rows to return (default 100)"New value: +"For TABLE_CONTENTS and TABLE_QUERY: max rows to return (default 100)" - changed
Input schema / properties / type / descriptionPrevious value: -"Object type to read (on-prem): PROG, CLAS, INTF, FUNC, FUGR, INCL, DDLS, DCLS, DDLX, BDEF, SRVD, SRVB, SKTD, TABL (transparent tables and DDIC structures), VIEW, DOMA, DTEL, MSAG, TRAN, TABLE_CONTENTS, DEVC, SOBJ, SYSTEM, COMPONENTS, TEXT_ELEMENTS, VARIANTS, BSP, BSP_DEPLOY, API_STATE, INACTIVE_OBJECTS, AUTH, FEATURE_TOGGLE, ENHO, VERSIONS, VERSION_SOURCE. Deprecated aliases: MESSAGES (use MSAG), FTG2 (use FEATURE_TOGGLE)."New value: +"Object type to read (on-prem): PROG, CLAS, INTF, FUNC, FUGR, INCL, DDLS, DCLS, DDLX, BDEF, SRVD, SRVB, SKTD, TABL (transparent tables and DDIC structures), VIEW, DOMA, DTEL, MSAG, TRAN, TABLE_CONTENTS, TABLE_QUERY, DEVC, SOBJ, SYSTEM, COMPONENTS, TEXT_ELEMENTS, VARIANTS, BSP, BSP_DEPLOY, API_STATE, INACTIVE_OBJECTS, AUTH, FEATURE_TOGGLE, ENHO, VERSIONS, VERSION_SOURCE. Deprecated aliases: MESSAGES (use MSAG), FTG2 (use FEATURE_TOGGLE)." - changed
Input schema / properties / type / enumPrevious value: -[ - "PROG", - "CLAS", - "INTF", - "FUNC", - "FUGR", - "INCL", - "DDLS", - "DCLS", - "DDLX", - "BDEF", - "SRVD", - "SRVB", - "SKTD", - "TABL", - "VIEW", - "DOMA", - "DTEL", - "TRAN", - "TABLE_CONTENTS", - "DEVC", - "SOBJ", - "SYSTEM", - "COMPONENTS", - "MSAG", - "MESSAGES", - "TEXT_ELEMENTS", - "VARIANTS", - "BSP", - "BSP_DEPLOY", - "API_STATE", - "INACTIVE_OBJECTS", - "AUTH", - "FEATURE_TOGGLE", - "FTG2", - "ENHO", - "VERSIONS", - "VERSION_SOURCE" -]New value: +[ + "PROG", + "CLAS", + "INTF", + "FUNC", + "FUGR", + "INCL", + "DDLS", + "DCLS", + "DDLX", + "BDEF", + "SRVD", + "SRVB", + "SKTD", + "TABL", + "VIEW", + "DOMA", + "DTEL", + "TRAN", + "TABLE_CONTENTS", + "TABLE_QUERY", + "DEVC", + "SOBJ", + "SYSTEM", + "COMPONENTS", + "MSAG", + "MESSAGES", + "TEXT_ELEMENTS", + "VARIANTS", + "BSP", + "BSP_DEPLOY", + "API_STATE", + "INACTIVE_OBJECTS", + "AUTH", + "FEATURE_TOGGLE", + "FTG2", + "ENHO", + "VERSIONS", + "VERSION_SOURCE" +] - added
Input schema / properties / whereAdded value: +{ + "description": "For TABLE_QUERY: structured WHERE conditions, ANDed together. Each item: {field, op, value?}. Allowed ops: =, !=, <>, <, <=, >, >=, LIKE, NOT LIKE, IN, NOT IN, IS NULL, IS NOT NULL. For IN/NOT IN: value must be a comma-separated list of single-quoted literals, e.g. \"'261','262'\". Subqueries are not allowed. Example: [{\"field\":\"MATNR\",\"op\":\"=\",\"value\":\"300006888\"},{\"field\":\"BUDAT_MKPF\",\"op\":\">=\",\"value\":\"20250101\"}].", + "items": { + "properties": { + "field": { + "description": "SAP field name (uppercase)", + "type": "string" + }, + "op": { + "description": "Comparison operator", + "type": "string" + }, + "value": { + "description": "Value to compare (omit for IS NULL / IS NOT NULL)", + "type": "string" + } + }, + "required": [ + "field", + "op" + ], + "type": "object" + }, + "type": "array" +}
8 tool updates
v0.9.6- Added
SAPContext - Added
SAPDiagnose - Added
SAPLint - Added
SAPManage - Added
SAPNavigate - Added
SAPRead - Added
SAPSearch - Added
SAPTransport
8 tool updates
v0.9.3- Removed
SAPContext - Removed
SAPDiagnose - Removed
SAPLint - Removed
SAPManage - Removed
SAPNavigate - Removed
SAPRead - Removed
SAPSearch - Removed
SAPTransport
1 tool update
v0.9.2- Changed
SAPRead1 field changed- added
Input schema / properties / maxResultsAdded value: +{ + "description": "For DEVC: max number of objects to list (default 200, clamped to [1, 1000]). Larger packages may be silently truncated by SAP at this limit; raise it if needed.", + "type": "number" +}
3 tool updates
v0.9.0- Changed
SAPNavigate1 field changed- changed
Input schema / properties / objectType / descriptionPrevious value: -"For references action: filter where-used results by ADT object type in slash format (e.g., PROG/P, CLAS/OC, FUNC/FM, INTF/OI). On systems supporting the scope endpoint, only returns references from objects of the specified type. On older systems, the filter is ignored and all references are returned with a note."New value: +"For references action: filter where-used results by ADT object type in slash format (e.g., PROG/P, CLAS/OC, FUGR/FF, INTF/OI). On systems supporting the scope endpoint, only returns references from objects of the specified type. On older systems, the filter is ignored and all references are returned with a note."
- Changed
SAPRead2 fields changed- changed
Input schema / properties / type / descriptionPrevious value: -"Object type to read (on-prem): PROG, CLAS, INTF, FUNC, FUGR, INCL, DDLS, DCLS, DDLX, BDEF, SRVD, SRVB, SKTD, TABL, VIEW, STRU, DOMA, DTEL, TRAN, TABLE_CONTENTS, DEVC, SOBJ, SYSTEM, COMPONENTS, MESSAGES, TEXT_ELEMENTS, VARIANTS, BSP, BSP_DEPLOY, API_STATE, INACTIVE_OBJECTS, AUTH, FTG2, ENHO, VERSIONS, VERSION_SOURCE."New value: +"Object type to read (on-prem): PROG, CLAS, INTF, FUNC, FUGR, INCL, DDLS, DCLS, DDLX, BDEF, SRVD, SRVB, SKTD, TABL (transparent tables and DDIC structures), VIEW, DOMA, DTEL, MSAG, TRAN, TABLE_CONTENTS, DEVC, SOBJ, SYSTEM, COMPONENTS, TEXT_ELEMENTS, VARIANTS, BSP, BSP_DEPLOY, API_STATE, INACTIVE_OBJECTS, AUTH, FEATURE_TOGGLE, ENHO, VERSIONS, VERSION_SOURCE. Deprecated aliases: MESSAGES (use MSAG), FTG2 (use FEATURE_TOGGLE)." - changed
Input schema / properties / type / enumPrevious value: -[ - "PROG", - "CLAS", - "INTF", - "FUNC", - "FUGR", - "INCL", - "DDLS", - "DCLS", - "DDLX", - "BDEF", - "SRVD", - "SRVB", - "SKTD", - "TABL", - "VIEW", - "STRU", - "DOMA", - "DTEL", - "TRAN", - "TABLE_CONTENTS", - "DEVC", - "SOBJ", - "SYSTEM", - "COMPONENTS", - "MESSAGES", - "TEXT_ELEMENTS", - "VARIANTS", - "BSP", - "BSP_DEPLOY", - "API_STATE", - "INACTIVE_OBJECTS", - "AUTH", - "FTG2", - "ENHO", - "VERSIONS", - "VERSION_SOURCE" -]New value: +[ + "PROG", + "CLAS", + "INTF", + "FUNC", + "FUGR", + "INCL", + "DDLS", + "DCLS", + "DDLX", + "BDEF", + "SRVD", + "SRVB", + "SKTD", + "TABL", + "VIEW", + "DOMA", + "DTEL", + "TRAN", + "TABLE_CONTENTS", + "DEVC", + "SOBJ", + "SYSTEM", + "COMPONENTS", + "MSAG", + "MESSAGES", + "TEXT_ELEMENTS", + "VARIANTS", + "BSP", + "BSP_DEPLOY", + "API_STATE", + "INACTIVE_OBJECTS", + "AUTH", + "FEATURE_TOGGLE", + "FTG2", + "ENHO", + "VERSIONS", + "VERSION_SOURCE" +]
- Changed
SAPTransport3 fields changed- changed
Input schema / properties / action / descriptionPrevious value: -"list: show transports (defaults to current user, modifiable only). get: fetch transport details including tasks and objects. create: create a new transport request. release: release a single transport or task. delete: delete a transport (use recursive=true to delete tasks first). reassign: change transport owner (use recursive=true for tasks too). release_recursive: release all unreleased tasks first, then the transport itself. check: check if a transport is needed for a package/object (requires type, name, package). history: list transports referencing an object (reverse lookup; requires type, name; works without SAP_ALLOW_TRANSPORT_WRITES)."New value: +"list: show transports (defaults to current user, modifiable only). get: fetch transport details including tasks and objects. create: create a new transport request (description required; package optional, defaults to $TMP — pass an explicit package to influence the transport route/type). release: release a single transport or task. delete: delete a transport (use recursive=true to delete tasks first). reassign: change transport owner (use recursive=true for tasks too). release_recursive: release all unreleased tasks first, then the transport itself. check: check if a transport is needed for a package/object (requires type, name, package). history: list transports referencing an object (reverse lookup; requires type, name; works without SAP_ALLOW_TRANSPORT_WRITES)." - changed
Input schema / properties / package / descriptionPrevious value: -"Package name (for check action)"New value: +"Package name. For create: optional — defaults to $TMP, pass an explicit package to influence the transport route (SAP infers K/W/T from the package's TADIR route). For check: required." - changed
Input schema / properties / type / descriptionPrevious value: -"For create: transport type K=Workbench (default), W=Customizing, T=Transport of Copies. For check/history: object type (PROG, CLAS, DDLS, etc.)"New value: +"Object type for check/history actions (PROG, CLAS, DDLS, etc.). Not used by create — the SAP backend infers transport type (K/W/T) from the package's TADIR route on the CreateCorrectionRequest endpoint."
TDQS
Scored across 8 tools
Each tool has a primary domain—navigation, diagnostics, transport, source read, search, context/dependency analysis, linting, and system management—and descriptions include explicit cross-references to reduce confusion. The main ambiguity is between SAPNavigate(references) and SAPContext(usages), both of which can answer 'who calls this?', and between SAPRead's grep and SAPSearch for finding code.
All tool names share the SAP prefix and CamelCase style, and most are concise action words like Read, Search, Lint, Manage, Navigate, and Diagnose. Context and Transport are noun-like rather than verb-like, a minor deviation, but the overall convention is consistent.
Eight top-level tools is well-scoped for a broad SAP development and analysis server. Each tool has a distinct domain, and the count sits comfortably in the ideal 3–15 range even though several tools expose many sub-actions.
The set thoroughly covers reading, searching, understanding, linting, diagnosing, transporting, and package/FLP management. However, the quickfix and lint_and_fix workflows explicitly reference SAPWrite/SAPActivate to persist changes, and those tools are absent from this server, creating a significant dead end for edit/activate tasks.
Maintenance
Related MCP Connectors
MCP server for Support & Service Management
MCP server for Product Management
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceMCP Server for Nutanix Prism Central13MIT
- MIT
- AlicenseBqualityBmaintenanceABAP Development Tools MCP server with comprehensive tooling and documentation for SAP systems193185 npm92Apache 2.0
- AlicenseBqualityCmaintenanceMCP server for SAP ABAP development that enables AI assistants and code editors to interact with SAP systems via ABAP Developer Toolkit (ADT) APIs, supporting read, create, update, and delete of ABAP objects.10072 npmMIT