langchain-mcp
Provides semantic search across the entire LangChain ecosystem, including documentation and source code for LangChain, LangGraph, LangSmith, and DeepAgents.
README
<div align="center">
LangChain MCP
Give your AI assistant complete knowledge of LangChain, LangGraph & LangSmith
Website • Installation • Features • Documentation
</div>
Overview
LangChain MCP is a Model Context Protocol (MCP) server that provides semantic search across the entire LangChain ecosystem. Build AI applications faster with instant access to documentation and source code for LangChain, LangGraph, LangSmith, and DeepAgents.
<img src="img/homepage.png" alt="LangChain MCP Homepage" width="800">
Features
- Semantic Search - Natural language queries across all LangChain ecosystem docs
- Source Code Search - Find code examples in Python and JavaScript repositories
- MCP Protocol - Works seamlessly with Claude Code, Claude Desktop, Cursor, and any MCP-compatible client
- Production Ready - Scalable API with authentication and usage tracking
- Fast & Accurate - Powered by ChromaDB and OpenRouter embeddings
Installation
Quick Start (Recommended)
# Install globally
npm install -g langchain-mcp
# Login with Google
langchain-mcp login
# Add to Claude Code
claude mcp add langchain-mcp -- npx langchain-mcp
Manual Configuration
Add the following configuration to your client's config file:
Claude Desktop
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Cursor
- macOS/Linux:
~/.cursor/mcp.json - Windows:
%USERPROFILE%\.cursor\mcp.json
{
"mcpServers": {
"langchain-mcp": {
"command": "npx",
"args": ["langchain-mcp"]
}
}
}
Usage
CLI Commands
langchain-mcp login # Login via Google OAuth
langchain-mcp status # Check usage and remaining credits
langchain-mcp logout # Logout and clear credentials
Available MCP Tools
| Tool | Description | Parameters |
|---|---|---|
search_docs |
Search documentation, references, and tutorials | query, limit (default: 5) |
search_langchain_code |
Search LangChain source code | query, language (py/js), limit |
search_langgraph_code |
Search LangGraph source code | query, language (py/js), limit |
search_deepagents_code |
Search DeepAgents source code | query, language (py/js), limit |
Pricing
- Free tier available for new users
- Donation bonus for supporters
Documentation
Self-deploy
Project Structure
langchain-MCP/
├── packages/
│ ├── ingest/ # Python - Data ingestion (uv)
│ ├── api/ # TypeScript - API server (Express)
│ ├── mcp-server/ # TypeScript - MCP client (npm package)
│ └── mcp-server-local/ # TypeScript - Local MCP server (dev)
├── config/
│ └── settings.json # Shared configuration
└── deploy.sh # Deployment script
Architecture
<img src="img/Architecture.png" alt="Architecture" width="600">
Setup Development Environment
1. Ingest Documentation & Source Code
cd packages/ingest
uv sync
uv run ingest --list # List available repositories
uv run ingest docs # Ingest documentation only
uv run ingest # Ingest all (docs + code)
2. Run API Server
cd packages/api
npm install
npm run dev # Development server on port 3000
3. Test Local MCP Server
cd packages/mcp-server-local
npm install
npm run dev
Configuration
All settings in config/settings.json:
{
"embedding": {
"provider": "openrouter",
"model": "qwen/qwen3-embedding-8b"
},
"chromadb": {
"path": "./data/chroma"
},
"chunking": {
"docs": { "chunk_size": 2000, "chunk_overlap": 200 },
"code": { "chunk_size": 4000, "chunk_overlap": 200 }
},
"repos": [
{
"name": "langchain",
"url": "https://github.com/langchain-ai/langchain",
"type": "code",
"languages": ["python", "javascript"]
}
]
}
Supported Embedding Providers
sentence-transformer(local)openaicoheregoogleollamaopenrouter(default)
See ChromaDB Integrations for more options.
Deployment
The project includes automated deployment scripts for VPS hosting:
# Manual deployment
./deploy.sh
# GitHub Actions (production branch)
git push origin main:production
Deployment includes:
- Code synchronization via rsync
- Automatic npm installation and build
- PM2 process management
- Nginx static file serving
- Environment variable management
Roadmap
- [x] Semantic search across docs and code
- [x] Google OAuth authentication
- [x] Usage tracking and credits system
- [x] MCP registry registration
- [x] Claude Code, Desktop, and Cursor support
- [ ] Rate limiting (per user / per IP)
- [ ] Additional embedding model options
- [ ] Local mode (no API key required)
- [ ] Browser extension for quick searches
- [ ] VSCode extension integration
Contributing
Forking and contributions are welcome!
Support
- Website: langchain-mcp.xyz
- Issues: GitHub Issues
- Donate: Support development at Ko-fi
License
MIT License - see the LICENSE file for details.
<div align="center">
Built with ❤️ by baixianger
</div>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。