Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@LangChain Anthropic MCP Servercreate a RAG chain using Claude Sonnet and Supabase"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
LangChain Anthropic MCP Server
🚀 MCP server that exposes LangChain + Anthropic Claude capabilities as tools - instantly generate production-ready RAG systems, Supabase vector stores, document ingestion pipelines, and more!
Perfect for use with Cursor AI or any MCP client.
🚀 Quick Start
Installation for Cursor
Add to your Cursor mcp.json:
That's it! Restart Cursor and start using it.
💡 Usage
Once installed, ask your AI assistant:
The AI will call the appropriate tool and return complete, production-ready code!
🛠️ Available Tools
✅ setup_supabase_vectorstore - Complete Supabase vector store setup
✅ create_rag_chain - Full RAG with Claude
✅ generate_document_ingestion - Document loading & chunking
✅ create_conversational_rag - RAG with conversation memory
✅ setup_hybrid_search - Vector + keyword search
✅ create_multi_query_retriever - Multi-query for better recall
✅ setup_extended_thinking - Extended thinking configuration
✅ generate_package_setup - Complete dependencies
📝 License
MIT License
Built with ❤️ for the LangChain and MCP community