abap-config-mcp

Search IMG / SPRO Activities

img_search

Read-onlyIdempotent

Search SAP IMG/SPRO customizing activities by keyword and namespace, returning activity IDs, titles, maintenance objects, and object patterns for targeted configuration lookup.

Instructions

Search the SAP Implementation Guide (IMG / SPRO) for customizing activities by keyword, using the IMG index (CUS_IMGACT activity titles) joined to the maintenance object. Returns activity IDs, SPRO titles, maintenance objects, and their pattern (V=view→VDAT, S=table→TABU, C=cluster→CDAT, T=transaction, D=doc). Pass namespace to scope (e.g. '/POSDW/' for POS DTA) — recommended, and required for free-text matching on this system since its SQL endpoint blocks LIKE scans.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "keyword": "<keyword>"
    },
    "name": "img_search"
  }
}

Input Schema

Name	Required	Description
`keyword`	Yes	Title keyword, matched case-insensitively (e.g. 'tender', 'profile', 'tax type')
`language`	No	Language key (default: E)
`namespace`	No	Activity-ID prefix to scope the search, e.g. '/POSDW/' (POS DTA). Strongly recommended.
`maxResults`	No	Max activities scanned within the scope (default: 200)
`inScopeOnly`	No	Keep only activities in the client's activated scope (CUS_IMGACH_SCOPE). Ignored when no scoping data exists.
`connectionId`	No	SAP system connection ID

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.16.0Nov 12, 2026

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare read-only, idempotent, open-world behavior. Beyond that, the description discloses the CUS_IMGACT-to-maintenance-object join, the returned fields, the pattern legend, and the SQL-endpoint LIKE-scan limitation, which is meaningful operational context. It does not discuss permissions or authentication requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It uses two front-loaded sentences, each of which earns its place by carrying purpose, returned fields, pattern semantics, and a system constraint. There is no filler or redundant restatement of the title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Because there is no output schema, the description helpfully supplies the return fields and decodes the pattern values. It leaves minor gaps around maxResults semantics (scanned vs. returned) and does not mention inScopeOnly, though those are covered by schema descriptions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the baseline is 3. The description adds real meaning for the namespace parameter: why it is recommended and why it becomes required for free-text matching on this system; other parameters rely on the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

It states a specific verb ('Search'), resource ('SAP Implementation Guide (IMG / SPRO) customizing activities'), and retrieval mechanism ('by keyword, using the IMG index ... joined to the maintenance object'). This clearly separates it from ABAP object/table searches and customizing read/apply siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly advises passing namespace to scope the search and says it is required for free-text matching on this system, which is actionable usage guidance. It does not name alternative tools or when not to use this tool, so it falls 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.

Deploy Server