{"type":"mcp_client","name":"langgraph-mcp","description":"This repository showcases a Universal Assistant built with LangGraph and Model Context Protocol (MCP), enabling seamless integration of language models with external data sources and tools through a multi-agent workflow.","category":"AI","language":"Python","stars":582,"forks":71,"owner":"esxr","github_url":"https://github.com/esxr/langgraph-mcp","homepage":null,"setup":"## Setup\n\n1.  Create and activate a virtual environment\n    ```bash\n    git clone https://github.com/esxr/langgraph-mcp.git\n    cd langgraph-mcp\n    python3 -m venv .venv\n    source .venv/bin/activate\n    ```\n\n2.  Install Langgraph CLI\n    ```bash\n    pip install -U \"langgraph-cli[inmem]\"\n    ```\n    Note: \"inmem\" extra(s) are needed to run LangGraph API server in development mode (without requiring Docker installation)\n\n3.  Install the dependencies\n    ```bash\n    pip install -e .\n    ```\n\n4.  Configure environment variables\n    ```bash\n    cp env.example .env\n    ```\n\n    Add your `OPENAI_API_KEY`, `GITHUB_PERSONAL_ACCESS_TOKEN` etc. to the `.env`\n\n    **Note**: We have added support for *Milvus Lite Retriever* (support file based URI). Milvus Lite won't work on Windows. For Windows you may need to use Milvus Server (Easy to start using Docker), and change the `MILVUS_DB` config to the server based URI. You may also enhance the [retriever.py](src/langgraph_mcp/retriever.py) to add retrievers for your choice of vector databases!","tools":"## Available Tools\n\n1.  Model Context Protocol (MCP) (Enables seamless integration between LLM applications and external data sources and tools.)\n2.  LangGraph (Framework for integrating language models into complex workflows.)\n3.  Universal Assistant (Combines LangGraph with MCP to implement a multi-agent pattern.)\n4.  Router (Directs user messages to the appropriate agent.)\n5.  MCP Wrapper (Provides a generic interface for interacting with MCP servers.)\n6.  Milvus Lite Retriever (Support file based URI for vector database.)","faq":null,"created_at":"2025-01-10T07:40:37+00:00","updated_at":"2025-03-28T16:16:57+00:00","source_url":"https://model-context-protocol.com/clients/langgraph-universal-assistant-model-context-protocol","related_articles":[]}