Docs Auditor MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_TOKEN | No | Optional GitHub token for higher GitHub API rate limits. |
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": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fetch_repo_structureA | List files in a local directory or GitHub repository. Use this first before reading docs. |
| read_docsA | Read README and docs/* from a local path or GitHub repo. Call after fetch_repo_structure. |
| cross_check_snippetsB | Extract fenced code blocks from docs and verify referenced files, imports, exports, call arity, and npm scripts against the repo. |
| analyze_open_issuesB | Search open GitHub issues related to docs, README, or quickstart gaps. |
| generate_fix_patchB | Propose concrete before/after doc patches for findings from a docs audit. |
| run_full_auditA | Run the full multi-step docs audit pipeline: structure → docs → cross-check → env drift → issues → fix patches. Returns markdown report + structured JSON. Also updates audit://report/latest. |
| apply_doc_patchesA | Apply proposed documentation patches to a local checkout. Defaults to dryRun=true and returns unified diffs. Set dryRun=false to write files. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| audit-quickstart | Run a full docs/quickstart audit and produce a DevRel-ready prioritized fix report. |
| fix-drift | Guide the model to review unified diffs and apply documentation patches safely (dry-run first). |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| latest-audit-report | Most recent structured JSON + Markdown audit report produced by run_full_audit or prompts. |
TDQS
Scored across 7 tools
Most tools have clearly distinct purposes: inspecting structure, reading docs, cross-checking snippets, analyzing issues, generating patches, and applying patches. The main overlap is run_full_audit, which duplicates the individual pipeline steps and also returns fix patches, but its description makes the orchestration role clear enough to avoid serious misselection.
All tool names use snake_case and follow a predictable verb-first pattern: fetch_*, read_*, cross_check_*, analyze_*, generate_*, run_*, apply_*. The convention is consistent throughout the set.
Seven tools is well-scoped for a docs auditing server, with each tool covering a meaningful step in the audit workflow. The full-audit convenience tool is justified alongside the granular tools rather than feeling like padding.
The surface covers the core docs audit lifecycle: inspect repo structure, read docs, verify snippets, search issues, generate patches, and apply them. Minor gaps remain, such as no standalone env-drift tool despite run_full_audit mentioning it, and patch application limited to local checkouts rather than remote PR creation.