The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Docs listing page.
Documentation generation tools for AI agents, served via the Model Context Protocol (MCP).
mcp-docs-tools provides five specialized documentation tools accessible through MCP:
| Tool | Description |
|---|---|
generate_jsdoc | Generate JSDoc/TSDoc comments from function signatures |
analyze_readme | Analyze README completeness and suggest improvements |
generate_changelog | Generate CHANGELOG entries from commit messages |
generate_api_docs | Generate REST API documentation from endpoint definitions |
analyze_code_comments | Analyze comment coverage, find TODOs, detect undocumented functions |
Add to your MCP client configuration:
Parses a function signature and generates JSDoc/TSDoc with @param, @returns, @throws, and @example tags.
Parameters:
functionSignature (string, required) - The function signature to documentdescription (string, optional) - Description of the functionincludeExample (boolean, optional, default: true) - Whether to include an @example tagAnalyzes README content for required sections (Installation, Usage, License, etc.), rates completeness from 0-100, and suggests missing sections.
Parameters:
content (string, required) - Full text content of the README fileGenerates CHANGELOG entries from git-style commit messages following the Keep a Changelog format. Categorizes commits as Added, Changed, Fixed, Removed, Deprecated, or Security.
Parameters:
versions (array, required) - Array of { version, date, commits } objectsprojectName (string, optional) - Project name for the headerGenerates REST API documentation in Markdown from endpoint descriptions including method, URL, parameters, request/response examples, and status codes.
Parameters:
apiTitle (string, required) - Title for the API documentationbaseUrl (string, optional) - Base URL for the APIapiDescription (string, optional) - General API descriptionendpoints (array, required) - Array of endpoint definitionsAnalyzes source code comment coverage: computes comment-to-code ratio, finds TODO/FIXME/HACK markers, detects functions without documentation, and suggests where docs are needed.
Parameters:
code (string, required) - Source code to analyzelanguage (string, optional, default: "typescript") - Programming languageNo additional configuration required. The server runs over stdio.
MIT