What is MCP Tool Langgraph Integration?
MCP Tool Langgraph Integration is an example project that demonstrates how to integrate MCP endpoint tools into a Langgraph tool node, consisting of two nodes: agent and tool.
How to use MCP Tool Langgraph Integration?
To use this project, ensure you have Python 3.11 installed. You can run the project from the source using the command uv run mcp_langgraph_tools after setting up the necessary API keys in a .env file.
Key features of MCP Tool Langgraph Integration?
- Integration of MCP tools with Langgraph.
- Simple setup with Python 3.11.
- Support for Brave Search tools through the MCP Server.
Use cases of MCP Tool Langgraph Integration?
- Integrating AI tools into applications using Langgraph.
- Building custom agent-tool interactions for various applications.
- Utilizing Brave Search tools in conjunction with AI models.
FAQ from MCP Tool Langgraph Integration?
- What are the prerequisites for using this project?
You need Python 3.11, and it's recommended to use the
uvpackage for running the project.
- How do I obtain the necessary API keys?
You can get a free API key for Brave Search from https://brave.com/search/api/ and you will need an API key for the AI provider, which can be set in the .env file.
- Is this project open for contributions?
Yes! Contributions are welcome, and you can submit a Pull Request.
MCP Tool Langgraph Integration
Description
Example project of how to integrate MCP endpoint tools into a Langgraph tool node
The graph consists of only 2 nodes, agent and tool.
Prerequisites
To use this project, make sure you have Python 3.11.
uv is recommended
Linux and Mac
curl -LsSf https://astral.sh/uv/install.sh | sh
Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
MCP Server requirements
- This example uses the MCP Server sample
@modelcontextprotocol/server-brave-searchto add Brave Search tools. This requires that you havenodeandnpxinstalled.
API Keys
- The MCP Server sample used is for Brave Search, you can get a free API key from https://brave.com/search/api/
- You will need and API key for the chosen AI provider which defaults to Anthropic but can be changed by editing the
__main__.pyfile - Put all api keys in a .env file in the repository root.
From source Usage
uv run mcp_langgraph_tools
Multiple MCP servers at one time
Check the multi_server branch for a more advanced example of how to use multiple MCP servers at once.
Whats New
- Version 0.1.0:
- Initial release
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Author
Paul Robello - probello@gmail.com
