jvelilla/langgraph_mcp
If you are the rightful owner of langgraph_mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
LangGraph Documentation MCP Server provides access to LangGraph documentation through a vector store-based retrieval system using Ollama for embeddings.
The LangGraph Documentation MCP Server is a sophisticated implementation that allows users to access LangGraph documentation efficiently. It leverages a vector store-based retrieval system, utilizing SKLearnVectorStore for document storage and retrieval. The server is built on the FastMCP framework and uses Ollama embeddings for document vectorization. This setup supports both tool-based queries and full documentation access, making it a versatile solution for developers and researchers working with LangGraph. The project is based on the MCP From Scratch tutorial and has been enhanced to incorporate modern embedding techniques. It requires Python 3.12+, Ollama, and several Python packages to function correctly. The server is designed to be easy to set up and use, with clear instructions for installation and operation.
Features
- Vector store-based document retrieval using SKLearnVectorStore
- Ollama embeddings for document vectorization
- MCP server implementation with FastMCP
- Document loading and processing from LangGraph documentation
- Support for both tool-based queries and full documentation access
Usages
local integration stdio
python mcp.run(transport='stdio') # Tools defined via @mcp.tool() decorator
local integration subprocess
python command='uv', args=['run', 'langgraph_mcp.py'] # Launch using virtual environment
remote integration sse
python mcp.run(transport='sse', host="0.0.0.0", port=8000) # Specify SSE endpoint
remote integration streamable http
yaml
paths:
/mcp:
post:
x-ms-agentic-protocol: mcp-streamable-1.0 # Copilot Studio integrationdevelopment framework fastmcp
python
from mcp.server import FastMCP
app = FastMCP('demo')
@app.tool()
async def query(): ...Tools
langgraph_query_tool
A tool that queries LangGraph documents through semantic search
Full Documentation Access
Accessing the full LangGraph documentation through resource endpoints
