docorbit
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| logging | {} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_docsB | Search documentation chunks using hybrid FTS5 ranking, symbol awareness, and optional version filtering. |
| get_docC | Retrieve a specific documentation page or contextual chunk by ID or URL with complete metadata and security annotations. |
| find_apiB | Lookup structured OpenAPI endpoints by path, operation ID, or keyword with exact parameters, schemas, auth, and error responses. |
| find_exampleB | Find verified, framework-specific code examples by task, language, framework, or target API. |
| find_pitfallB | Search documented pitfalls, gotchas, deprecations, breaking changes, and runtime restrictions. |
| find_recipeC | Assemble an evidence-grounded implementation recipe with explicit prerequisites, ordered steps, and validation steps. |
| get_versionC | Inspect workspace dependencies and resolve the exact compatible documentation version using the SemVer confidence ladder. |
| list_sourcesC | List all indexed documentation sources, snapshot records, doc versions, and machine-readability status. |
| get_implementation_contextB | High-level documentation intelligence orchestrator. Automatically resolves workspace dependencies and versions, detects task intent, retrieves relevant chunks, APIs, verified examples, and pitfalls, and compiles an evidence-grounded recipe within a strict token budget. |
| check_apiA | Verify agent/generated code against indexed OpenAPI schemas and documentation. Detects invalid endpoints, wrong HTTP methods, missing required parameters, deprecations, removed APIs, version syntax conflicts, and response assumptions. Distinguishes verified, warning, mismatch, and insufficient_evidence. |
| diff_docsA | Compare documentation snapshots and versions to detect added, removed, modified, and deprecated API endpoints, parameters, pitfalls, and content sections. Produces deterministic diffs ignoring formatting-only changes. |
| analyze_impactB | Compare detected documentation and API changes against current project workspace files. Identifies affected files, exact line numbers, code snippets, matched patterns, and traceable reasons with certainty rankings (high, medium, heuristic). |
| get_documentation_mapB | Retrieve the hierarchical documentation map, page tree, section headings, and estimated token budget footprints for indexed documentation. |
| export_agent_contextB | Deterministically generate and export agent-native documentation context files (AGENTS.md, CLAUDE.md, skill.md, llms.txt, docs-map.md) grounded in project dependency versions and authoritative documentation. |
| ingest_docA | Ingest, crawl, parse, and index authoritative documentation from any URL or raw content directly into DocOrbit. Tracks documentation sources deterministically in docs.lock. Extracts semantic chunks, OpenAPI endpoints, code examples, and pitfalls. If taskContext is provided, immediately synthesizes and returns an evidence-grounded implementation recipe with exact code and API details. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Indexed Documentation Sources | Collection of all indexed documentation sources, version status, and snapshots. |
TDQS
Scored across 15 tools
Each tool targets a distinct retrieval or analysis mode (search vs. map vs. API lookup vs. examples vs. pitfalls vs. recipes), so boundaries are mostly clear. The main overlap is get_implementation_context, which is an orchestrator that subsumes search_docs, find_api, find_example, find_pitfall, and find_recipe, but its explicit 'high-level orchestrator' labeling mitigates confusion.
All 15 tools follow a consistent snake_case verb_noun pattern (list_sources, search_docs, get_doc, find_api, check_api, diff_docs, analyze_impact, export_agent_context, ingest_doc). The verb variety (get/find/check/diff/analyze) is intentional and readable, not chaotic.
At 15 tools, the set is well within a healthy range and each tool maps to a distinct capability in the documentation-intelligence workflow. No obvious filler or redundant tools inflate the count.
The surface covers the full lifecycle: ingest/index (ingest_doc), discovery (list_sources, get_documentation_map), retrieval (search_docs, get_doc, find_api, find_example, find_pitfall), synthesis (find_recipe, get_implementation_context), verification (check_api), change tracking (diff_docs, analyze_impact), and export (export_agent_context). Version resolution (get_version) rounds out dependency-aware workflows, leaving no obvious dead ends.