# langchain-ai/langchain-mcp-adapters

LangChain 🔌 MCP

Repository: https://github.com/langchain-ai/langchain-mcp-adapters
Canonical: https://ross.abutalabs.com/products/langchain-mcp-adapters
Homepage: https://docs.langchain.com/oss/python/langchain/mcp
Language: Python
License: MIT
License Family: permissive
Topics: langchain, langgraph, mcp, python, tools
Last push: 2026-08-26T18:27:12+00:00

## Health v2 (maintenance only)
Score: 86/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 96, longevity 40
- inputs: {"age_days": 572, "days_push": 7, "days_rel": 27, "gap_med": 9.5, "n_releases_24m": 29}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3642, forks 482 (observed 2026-08-28T04:08:12.831020+00:00)

## What it is
A lightweight Python library that adapts Anthropic Model Context Protocol (MCP) tools into LangChain/LangGraph-compatible tools. It provides a client (MultiServerMCPClient) that connects to one or more MCP servers over stdio or HTTP and loads their tools for use by LangGraph agents.

## Use cases
- use MCP server tools inside a LangGraph agent
- connect a LangChain agent to multiple MCP servers
- load tools from an MCP server over stdio or HTTP
- bridge Model Context Protocol tools with LangChain
- build agents that call tools exposed via MCP

## When to choose
- you build agents with LangChain or LangGraph and want to consume MCP tools
- you need to aggregate tools from several MCP servers into one agent
- you want a maintained, official adapter between MCP and the LangChain ecosystem

## When to avoid
- you use a different agent framework without LangChain/LangGraph
- you need a JavaScript/TypeScript adapter (use the langchainjs version instead)
- you only need a standalone MCP client without LangChain integration

## Facets
- artifact type: library
- maturity: active
- function: mcp, agent-framework, sdk, middleware
- domain: large-language-models, developer-tools, apis
- platform: python, cross-platform
- tags: langchain, langgraph, model-context-protocol, tool-integration, mcp-client, ai-agents

## Member repositories
- langchain-ai/langchain-mcp-adapters (main) score 86

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:12.831020+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:31:47.087242+00:00, confidence not recorded.
  - readme: https://github.com/langchain-ai/langchain-mcp-adapters (fetched 2026-08-28T04:08:12.831020+00:00, sha 8a66f5e6a012)
  - homepage: https://docs.langchain.com/oss/python/langchain/mcp (fetched 2026-08-29T09:26:15.419413+00:00, sha eaaa2dfb0807)
  - site_page: https://docs.langchain.com/ (fetched 2026-08-29T09:26:15.422587+00:00, sha e6cbe67a291c)
  - site_page: https://docs.langchain.com/oss/python/integrations/providers/overview (fetched 2026-08-29T09:26:15.424369+00:00, sha 8260e6c475ce)
  - site_page: https://docs.langchain.com/oss/python/langchain/install (fetched 2026-08-29T09:26:15.426233+00:00, sha f72550dc8995)
  - site_page: https://docs.langchain.com/oss/python/langchain/quickstart (fetched 2026-08-29T09:26:15.428211+00:00, sha ee8c6d60528c)
  - site_page: https://docs.langchain.com/oss/python/releases/changelog (fetched 2026-08-29T09:26:15.431325+00:00, sha 048dded673bc)
  - site_page: https://docs.langchain.com/langsmith/trace-with-langchain (fetched 2026-08-29T09:26:15.434245+00:00, sha 32a7ec425016)
  - site_page: https://docs.langchain.com/use-these-docs (fetched 2026-08-29T09:26:15.436598+00:00, sha 5ab7220bb555)
- Data as of 2026-08-30T08:39:29.467469+00:00.