MCP + LangGraph Agent
@hirokiyn
About MCP + LangGraph Agent
LangGraph agent tutorial adapted to use MCP servers.
Config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is MCP + LangGraph Agent?
It is a minimal, functional example of an agent powered by LangGraph where tools are implemented using MCP (Model Context Protocol) servers instead of traditional LangChain tools. It is based on the official LangGraph tutorial and is intended as a skeleton for building custom LangGraph agents with MCP tools.
How to use MCP + LangGraph Agent?
Clone the repository, install dependencies using Poetry, and set the Anthropic API key in the .env file. Start the MCP servers (python src/mcp_servers/math_server.py and python src/mcp_servers/weather_server.py), then run poetry run main to launch the agent in interactive mode.
Key features of MCP + LangGraph Agent
- Integrates LangGraph for managing agent state and message routing.
- Uses MCP servers to provide access to tools.
- Includes example MCP servers for math and weather.
- Provides a command-line interface for interacting with the agent.
Use cases of MCP + LangGraph Agent
- Building a custom LangGraph agent with MCP-based tools.
- Experimenting with MCP integration in a LangGraph workflow.
- Prototyping an interactive CLI agent with math and weather capabilities.
- Using the project as a skeleton for rapid agent development.
FAQ from MCP + LangGraph Agent
What does this project demonstrate?
It demonstrates how to integrate MCP servers as tools in a LangGraph agent, using math and weather as example servers.
How do I install and run the agent?
Clone the repository, install dependencies with Poetry, set your Anthropic API key in .env, start the MCP servers, and run poetry run main for interactive mode.
Can I change the LLM used by the agent?
Yes, the LLM configuration can be changed in src/common.py.
How do I configure which MCP servers are used?
The MCP servers are configured in src/main.py; you can modify the configuration to add or remove servers, or to change the transport mechanism.
What are the example tools included?
The example tools are a math server and a weather server, each providing basic functions like arithmetic and weather data retrieval.
Frequently asked questions
What does this project demonstrate?
It demonstrates how to integrate MCP servers as tools in a LangGraph agent, using math and weather as example servers.
How do I install and run the agent?
Clone the repository, install dependencies with Poetry, set your Anthropic API key in `.env`, start the MCP servers, and run `poetry run main` for interactive mode.
Can I change the LLM used by the agent?
Yes, the LLM configuration can be changed in `src/common.py`.
How do I configure which MCP servers are used?
The MCP servers are configured in `src/main.py`; you can modify the configuration to add or remove servers, or to change the transport mechanism.
What are the example tools included?
The example tools are a math server and a weather server, each providing basic functions like arithmetic and weather data retrieval.
Basic information
More Reasoning MCP servers
End-to-End Agentic AI Automation Lab
MDalamin5This repository contains hands-on projects, code examples, and deployment workflows. Explore multi-agent systems, LangChain, LangGraph, AutoGen, CrewAI, RAG, MCP, automation with n8n, and scalable agent deployment using Docker, AWS, and BentoML.
MCP Sandbox
danstarnsTurn any JavaScript module into a sandboxed MCP (Model Context Protocol) server with automatic reflection and type inference.
quarkus-langchain4j-workshop
quarkusioQuarkus LangChain4J Workshop that demonstrates both single AI service capabilities and Agentic AI orchestration
Task Planner MCP Server
CaptainCrouton89An MCP (Model Context Protocol) server that helps AI assistants (like Claude) break down complex tasks into manageable steps, track progress, and manage a hierarchical task list.
Agenticstore — The Open Source Standard For Local Mcp Tooling
agenticstoreAgenticStore: The secure toolkit for AI agents. Instantly equip Claude Desktop, Cursor, and Windsurf with 27+ MCP tools, persistent memory, and SearXNG search, all protected by a built-in PII prompt firewall to protect your data from being exposed to AI agents.
Comments