trackmcp
Back to directory
chriswritescode-dev

codedox

View on GitHub

A powerful system for crawling documentation websites, extracting code snippets, and providing fast search capabilities via MCP (Model Context Protocol) integration.

22 stars PythonAI & Machine Learning Updated Oct 11, 2025

Documentation

CodeDox - AI-Powered Documentation Search & Code Extraction

Transform any documentation site into a searchable code database - CodeDox crawls documentation websites, intelligently extracts code snippets with context, and provides lightning-fast search via PostgreSQL full-text search and MCP (Model Context Protocol) integration for AI assistants.

📚 Documentation

For full documentation, installation guides, API reference, and more, visit:

**https://chriswritescode-dev.github.io/codedox/**

Quick Start

Docker Setup (Recommended)

bash
# Clone the repository
git clone https://github.com/chriswritescode-dev/codedox.git
cd codedox

# Configure environment
cp .env.example .env
# Edit .env to add your CODE_LLM_API_KEY (optional for AI-enhanced extraction)

# Run the automated setup
./docker-setup.sh

# Access the web UI at http://localhost:5173
# MCP tools available at http://localhost:8000/mcp

Manual Installation

See the full installation guide for detailed instructions.

Key Features

  • Intelligent Web Crawling: Depth-controlled crawling with URL pattern filtering and domain restrictions
  • Smart Code Extraction: Dual-mode extraction (Automatic Title / Description or LLM Generated Titles and Descriptions)
  • Enhanced Search Modes: Standard code search with intelligent markdown fallback for comprehensive results
  • Lightning-Fast Search: PostgreSQL full-text search with fuzzy matching
  • GitHub Repository Processing: Clone and extract documentation from GitHub repositories with full path support (e.g., `/tree/main/docs`)
  • HTTP-First MCP Integration: MCP tools via HTTP endpoints with Streamable HTTP transport support (MCP 2025-03-26 spec)
  • Full Documentation Access: Get complete markdown content from any documentation page for full context
  • Modern Web Dashboard: React + TypeScript UI for visual management
  • Version Support: Track multiple versions of documentation
  • Real-time Monitoring: Live crawl progress and health monitoring
  • Upload Support: Upload documentation directly or from GitHub repositories (useful for repos with doc sites)

Demo - MCP Integration Example - OpenCode TUI

Screenshots

Dashboard

Markdown Search with Highlighting

Source Detail View

Documentation

Contributing

See our Contributing Guide for details on how to contribute to CodeDox.

Author

Chris Scott - chriswritescode.dev

License

This project is licensed under the MIT License - see the LICENSE file for details.

Frequently asked questions

What is codedox?

codedox is A powerful system for crawling documentation websites, extracting code snippets, and providing fast search capabilities via MCP (Model Context Protocol) integration.

How do I install codedox?

Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.

Is codedox open source?

Yes — it is hosted on GitHub at https://github.com/chriswritescode-dev/codedox and has 22 stars.

Related MCP tools

All-Hands-AIopenhands

🙌 OpenHands: Code Less, Make More for the Model Context Protocol. Enhance AI assistants with powerful integrations. Python-based implementation.

64,677 Python
agentartificial-intelligencechatgpt+6
mem0aimem0

Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management. Python-based implementation.

42,646 Python
agentsaiai-agents+12
zhayujiechatgpt-on-wechat

基于大模型搭建的聊天机器人，同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入，可选择ChatGPT/Claude/DeepSeek/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Kimi/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。

39,573 Python
aiai-agentchatgpt+17
assafelovicgpt-researcher

An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations. Built for the Model Context Protocol to

24,026 Python
agentaiautomation+8
jlowinfastmcp

🚀 The fast, Pythonic way to build MCP servers and clients Trusted by 19900+ developers. Trusted by 19900+ developers. Trusted by 19900+ developers.

19,927 Python
agentsfastmcpllms+6
1Panel-devmaxkb

🔥 MaxKB is an open-source platform for building enterprise-grade agents. MaxKB 是强大易用的开源企业级智能体平台。 for the Model Context Protocol. Enhance AI assistants with po

19,062 Python
agentagentic-aichatbot+11

Run your own MCP server? See who uses it and what to fix.

Measure it with TrackMCP