AutoDocs MCP Server Documentation¶

🗺️ Choose Your Documentation Path¶

📚 Product Documentation

For Users & Integrators

Learn how to install, configure, and use AutoDocs MCP Server with your AI assistants. Includes API reference, troubleshooting, and integration guides.

Quick installation and setup
MCP tools and their usage
Configuration options
Troubleshooting guides

Start Using AutoDocs →

🏗️ Development Process

For Contributors & Technical Reviewers

Understand the system architecture, development standards, and how to contribute to the project. Essential for anyone working on or reviewing the codebase.

System architecture and design decisions
Development standards and workflows
Testing strategies and requirements
Contribution guidelines

Explore the Process →

📖 Development Journey

For AI-Development Enthusiasts

Follow the complete development story of this project, from initial concept to Phase 4 completion. See how "intention-only programming" works in practice.

Phase-by-phase evolution
Technical decisions and learnings
Development session insights
AI-assisted development patterns

Follow the Journey →

🚀 Quick Start¶

New to AutoDocs?

For immediate usage: Start with Product Documentation

For contributing: Check out Development Process

For the full story: Explore the Development Journey

Installation (Quick)¶

PyPI InstallationDevelopment Setup

# Install with uv (recommended)
uv tool install autodoc-mcp

# Start the MCP server
autodoc-mcp

# Clone and set up for development
git clone https://github.com/bradleyfay/autodoc-mcp.git
cd autodoc-mcp
uv sync --all-extras

# Run tests
uv run pytest

🎯 Project Overview¶

AutoDocs MCP Server is a fully implemented Model Context Protocol (MCP) server that provides AI assistants with intelligent, context-aware documentation for Python dependencies.

Key Features¶

🧠 Smart Dependency Context: Automatically includes relevant dependencies with intelligent relevance scoring
⚡ High Performance: Version-based caching with concurrent fetching (3-5 second response times)
🛡️ Production Ready: Circuit breakers, graceful degradation, comprehensive health monitoring
🔗 MCP Native: 8 comprehensive MCP tools for seamless AI integration

Architecture Highlights¶

Phase 4 Complete: Full dependency context system with smart scoping
277 Tests: Comprehensive test coverage with pytest ecosystem
Layered Architecture: Clean separation of concerns with 10 core service modules
Network Resilience: Exponential backoff, connection pooling, circuit breakers

🏆 Project Status¶

Phase 4 Complete ✅ Production Ready 🚀 Open Source 💚

Current Version: v0.4.2 Test Coverage: 277 comprehensive tests MCP Tools: 8 production-ready tools Architecture: Phase 4 layered design complete

Section	Best For	Key Content
📚 Product Docs	End users, integrators	Installation, usage, API reference, troubleshooting
🏗️ Development Process	Contributors, reviewers	Architecture, standards, testing, contributing
📖 Development Journey	Learning enthusiasts	Project evolution, decisions, AI-development insights