What is Rtfmbro Mcp

rtfmbro-mcp is a Model Context Protocol (MCP) server that provides real-time, version-aware documentation fetching for packages across multiple ecosystems, bridging the gap between AI agents and accurate, up-to-date package documentation.

Use cases

Use cases for rtfmbro-mcp include enhancing AI coding assistants with real-time documentation, improving developer efficiency by providing context-specific information, and ensuring that legacy projects have access to the correct documentation versions.

How to use

To use rtfmbro-mcp, integrate it into your MCP configuration by adding the server details. Once set up, it automatically fetches the relevant documentation based on the specific version of the package your project is using.

Key features

Key features include version-precise fetching, comprehensive coverage of documentation files, intelligent caching for fresh content, seamless integration with AI coding assistants, and a developer-friendly setup process.

Where to use

rtfmbro-mcp can be used in software development environments where accurate and up-to-date package documentation is crucial, particularly in projects utilizing Python, Node.js, and Swift.

rtfmbro-mcp

rtfmbro provides always-up-to-date, version-specific package documentation as context for coding agents. An alternative to context7.

https://github.com/user-attachments/assets/dbe0b3b4-a42c-4e91-8bcd-a94d430ef0b8

Demonstration of rtfmbro in use, fetching a specific version (3.1.1) of Flask’s readme and docs.

Overview

rtfmbro is a Model Context Protocol (MCP) server that provides real-time, version-aware documentation fetching for packages across multiple ecosystems. It bridges the gap between AI agents and accurate, up-to-date package documentation by fetching docs directly from GitHub repositories at the exact version your project uses.

Supported Ecosystems

Why rtfmbro?

The Problem

• Stale Documentation: AI models often rely on outdated training data about packages
• Missing Context: Source code in node_modules etc. lacks high-level documentation, browsing it is usually token-consuming and inefficient
• Version Mismatches: Generic documentation doesn’t match your specific package version, especially for legacy projects or brand new packages

The Solution

rtfmbro tries to solve these issues by:

1. Version-Precise Fetching: Retrieves documentation from the exact git tag/commit that matches your lockfile
2. Comprehensive Coverage: Extracts all documentation files (.md, .mdx, .txt, .rst, .html) from the repository
3. Intelligent Caching: SHA-based currency checking ensures docs stay fresh without unnecessary re-fetching
4. Agent Integration: Seamlessly integrates with AI coding assistants via the Model Context Protocol
5. Great DX: Zero seting up for developers, just add the server to your MCP configuration, instructions and start fetching docs

MCP Tools

The server exposes four primary tools to AI agents:

Installation & Setup

Quick Start

Claude Code

claude mcp add-json rtfmbro '{ "type": "http",  "url": "https://rtfmbro.smolosoft.dev/mcp/" }'

Claude Desktop / VS Code / etc.

Add the remote server to your MCP configuration:

{
  "rtfmbro": {
    "type": "http",
    "url": "https://rtfmbro.smolosoft.dev/mcp/"
  }
}

Cursor

Agent Integration

To truly integrate rtfmbro with your AI coding agent of choice, copy the appropriate meta-instruction file to your project:

• GitHub Copilot: Copy .github/copilot-instructions.md to your project
• Claude Code: Copy CLAUDE.md to your project root
• Cursor: Copy .cursor/rules to your project root
• Other agents: Adapt the instructions from either file above to your agent’s format

How It Works

Documentation Workflow

1. Registry Lookup: Queries the package registry (PyPI, npm, etc.) for metadata
2. GitHub Discovery: Extracts the GitHub repository URL from package metadata
3. Version Resolution: Fetches available git tags and matches them against your semantic version
4. Smart Fetching: Clones the repository at the exact matched tag/commit
5. Content Filtering: Extracts only documentation files, removing source code and build artifacts
6. Caching & Currency: Stores results with SHA-based currency checking for efficient re-access

Caching Strategy

• SHA-Based Validation: Compares current repository commit SHA with cached version
• Automatic Invalidation: Re-fetches documentation when new commits are detected
• Persistent Storage: Maintains local cache to avoid redundant GitHub API calls
• Metadata Preservation: Stores documentation tree structure for fast browsing

Prerequisites

• Package must be published to a supported registry (PyPI, npm)
• Package metadata must contain a valid GitHub repository link
• Repository must use git tags for version management
• Documentation files must be present in the repository (not just generated sites)

Roadmap

Near Term

• [x] Ecosystem independent fallback: Implement a fallback mechanism for unsupported ecosystems
• [ ] Provide rtfmbro source code: Open source the server codebase
• [ ] Public docker image: Create a public Docker image for easy deployment
• [ ] Private repo support: Allow authenticated access to private repositories
• [ ] Add Tests: Implement unit and integration tests for core functionality
• [ ] Enhanced Python Support: Include pydocs and docstring extraction
• [ ] Search Capabilities: Search across documentation corpus

Future Ecosystems / Languages / Registries

• [ ] Rust (crates.io)
• [ ] Go (pkg.go.dev)
• [ ] Java/Kotlin (Maven Central)
• [ ] C#/.NET (NuGet)
• [ ] Ruby (RubyGems)

Source code hosting and repository support:

• [x] GitHub: Support for GitHub repositories
• [ ] Gitlab: Support for GitLab repositories
• [ ] Bitbucket: Support for Bitbucket repositories
• [ ] Launchpad: Support for Launchpad repositories

Known Issues

• Some packages may have documentation in separate standalone repos
• Large repositories may take a bit of time to clone and process initially

Similar / Additive Projects

• mcp-package-docs: Another MCP server for package documentation, focusing on documentation extraction, LSP servers, etc. May be a great supplement to rtfmbro.
• rust-docs-mcp-server: MCP server for Rust documentation, focused on Rust-specific features and documentation formats.
• mcp-ragdocs: MCP server for RAG (Retrieval-Augmented Generation) documentation, aimed at improving the documentation experience for AI models.
• godoc-mcp: MCP server for Go documentation, providing access to Go package documentation via the Model Context Protocol.
• context7: Alternative to rtfmbro

Differences between context7 and rtfmbro