mcpField
D
docs

docs

Local
github.com/rog0xDeveloper Tools0Updated 32w ago
Repository

About docs

An MCP server for AI agents that generates and reviews JSDoc, README, changelog, and REST API documentation. It also checks source-code comment coverage and documentation gaps.

Key features

  1. 01Generate JSDoc and TSDoc
  2. 02Review README completeness
  3. 03Create changelog entries
  4. 04Generate REST API docs
  5. 05Find code comment gaps

Use cases

  1. 01Document functions from signatures
  2. 02Identify missing README sections
  3. 03Turn commit messages into changelog entries
  4. 04Review code for TODOs and undocumented functions

MCP support

Exposes five documentation generation and analysis tools to MCP clients over stdio.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "rog0x-docs": {
      "command": "npx",
      "args": [
        "-y",
        "@rog0x/mcp-docs-tools"
      ]
    }
  }
}
Run commandnpx -y @rog0x/mcp-docs-tools

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@rog0x/mcp-docs-tools1.0.2

Tools

5

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
descriptionstringNoOptional description of what the function does
includeExamplebooleanNoWhether to include an @example tag
functionSignaturestringYesThe function signature to document, e.g. 'async function fetchUser(id: string): Promise<User>'

Details

From the project README

mcp-docs-tools

Documentation generation tools for AI agents, served via the Model Context Protocol (MCP).

Overview

mcp-docs-tools provides five specialized documentation tools accessible through MCP:

ToolDescription
generate_jsdocGenerate JSDoc/TSDoc comments from function signatures
analyze_readmeAnalyze README completeness and suggest improvements
generate_changelogGenerate CHANGELOG entries from commit messages
generate_api_docsGenerate REST API documentation from endpoint definitions
analyze_code_commentsAnalyze comment coverage, find TODOs, detect undocumented functions

Installation

npm install
npm run build

Usage

As an MCP Server

Add to your MCP client configuration:

{
  "mcpServers": {
    "docs-tools": {
      "command": "node",
      "args": ["path/to/mcp-docs-tools/dist/index.js"]
    }
  }
}
Tools
generate_jsdoc

Parses a function signature and generates JSDoc/TSDoc with @param, @returns, @throws, and @example tags.

Parameters:

  • functionSignature (string, required) - The function signature to document
  • description (string, optional) - Description of the function
  • includeExample (boolean, optional, default: true) - Whether to include an @example tag
analyze_readme

Analyzes 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 file
generate_changelog

Generates 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 } objects
  • projectName (string, optional) - Project name for the header
generate_api_docs

Generates 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 documentation
  • baseUrl (string, optional) - Base URL for the API
  • apiDescription (string, optional) - General API description
  • endpoints (array, required) - Array of endpoint definitions
analyze_code_comments

Analyzes 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 analyze
  • language (string, optional, default: "typescript") - Programming language

Configuration

No additional configuration required. The server runs over stdio.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.