LangGraph MCP Server
About
A Python-based Model Context Protocol (MCP) server that enables LLMs to access external tools and resources through a standardized interface.
Details
- Author
- rezawr
- GitHub stars
- 1
- Downloads
- 374
- Categories
- Other
Jump to
- Modular clean architecture for maintainability
- Easy registration of new tools and resources
- Centralized configuration via config.py
- Built-in logging utilities
- Testable components in isolation
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
LangGraph MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Run the server with python -m app.server. Clients can then connect to it to call registered tools and resources.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"langgraph mcp server": {
"mcp-basic-architecture": {
"command": "python",
"args": [
"-m",
"app.server"
]
}
}
}
}McpServers
{
"mcp-basic-architecture": {
"command": "python",
"args": [
"-m",
"app.server"
]
}
}LangGraph MCP Server
A clean, modular implementation of a Model Context Protocol (MCP) server for LangGraph documentation.
Architecture
This project follows a clean architecture pattern to make the MCP server more maintainable and easier to debug as more functionality is added.
Directory Structure
app/
├── config.py # Configuration settings
├── server.py # Main server entry point
├── resources/ # Resources that can be accessed by clients
│ ├── __init__.py # Resource registration
│ └── langgraph_resources.py # LangGraph-specific resources
├── tools/ # Tools that can be called by clients
│ ├── __init__.py # Tool registration
│ └── langgraph_tools.py # LangGraph-specific tools
└── utils/ # Utility functions
├── __init__.py
└── logging_utils.py # Logging utilities
Core Components
1. Server: The main entry point that initializes the MCP server and registers all tools and resources.
2. Config: Central location for all configuration settings.
3. Tools: Functions that can be called by clients to perform specific tasks.
4. Resources: Data sources that can be accessed by clients.
5. Utils: Utility functions used throughout the application.
Adding New Functionality
Adding a New Tool
1. Create a new file in the app/tools/ directory (e.g., weather_tools.py).
2. Define your tool functions in this file.
3. Create a registration function (e.g., register_weather_tools).
4. Import and call this registration function in app/tools/__init__.py.
Example:
```python
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
