langgraph-mcp and mcp-langgraph

These are ecosystem siblings—one provides a reusable agent template with MCP integration, while the other is an educational tutorial showing how to adapt LangGraph agents to work with MCP servers, serving different user needs (ready-to-use vs. learning resource) within the same LangGraph-MCP integration space.

langgraph-mcp
27
Experimental
mcp-langgraph
23
Experimental
Maintenance 2/25
Adoption 7/25
Maturity 1/25
Community 17/25
Maintenance 2/25
Adoption 5/25
Maturity 1/25
Community 15/25
Stars: 32
Forks: 10
Downloads: —
Commits (30d): 0
Language: Python
License: —
Stars: 12
Forks: 5
Downloads: —
Commits (30d): 0
Language: Python
License: —
No License Stale 6m No Package No Dependents
No License Stale 6m No Package No Dependents

About langgraph-mcp

prsdm/langgraph-mcp

LangGraph agent template with MCP.

Implements automatic tool discovery across multiple MCP servers (web search, YouTube transcripts, math, weather) that LangGraph agents can dynamically invoke without hardcoding integrations. The architecture runs MCP servers separately and connects via a client-server pattern, enabling modular composition of external capabilities. Supports multi-server orchestration where agents automatically discover and select available tools based on task requirements.

About mcp-langgraph

hirokiyn/mcp-langgraph

LangGraph agent tutorial adapted to use MCP servers.

Related comparisons

langgraph-mcp and langchain-mcp-adapters langgraph-mcp and langchain-mcp-adapters

Scores updated daily from GitHub, PyPI, and npm data. How scores work