Langchain Agent With MCP Servers

This project demonstrates an intelligent agent based on LangChain, which integrates multiple service tools (search, weather, mathematical calculation) through the MCP protocol, adopts a modular design, and implements a perfect graceful shutdown mechanism.

Developer tools Search tools #Multi - tool Agent #Graceful Shutdown #Modular Design #MCP Protocol .Python

rating : 2 points

downloads : 9

update time : 2025-04-23

What is Model Context Protocol (MCP)?

MCP is a standardized protocol for transmitting model context information between different services. It allows developers to easily integrate various tools and services into a unified platform.

How to use MCP?

Users can start and manage the MCP server through simple command - line operations and utilize its various functions to complete tasks.

Applicable Scenarios

MCP is suitable for application scenarios that require rapid integration of multiple types of services, such as search engines, weather forecasting, and mathematical calculations.

Main Features

Search EngineSupports web search and news search functions to help users quickly find the information they need.

Weather InformationProvides real - time weather condition queries, making it convenient for users to understand the current or future weather changes in the next few days.

Mathematical CalculationCan parse and calculate complex mathematical expressions to meet users' calculation needs.

Advantages and Limitations

Advantages

Unified interface simplifies the development process.

Strong cross - platform compatibility, easy to expand new functions.

Powerful signal processing mechanism ensures stable operation of the service.

Limitations

Performance may need further optimization for some complex tasks.

There may be a certain learning cost during the initial setup.

How to Use

Install the MCP Server

After cloning the project repository and creating a virtual environment, run the installation script.

Configure Environment Variables

Fill in the API key and other configuration parameters as needed.

Start the MCP Service

Execute the main program to start using the MCP service.

Usage Examples

Search for Technology NewsUsers want to know the recent news reports about artificial intelligence.

Query the Weather in BeijingUsers want to know the weather conditions in Beijing on the current day.

Frequently Asked Questions

How to add a new MCP server?

Why do I need to configure the API key?

Related Resources

Official Documentation

Detailed documentation of the MCP protocol.

GitHub Code Repository

Source code and example projects.

🚀 Using LangChain Agents with MCP Servers

A LangChain agent integrated with Model Context Protocol (MCP) servers via the MCP adapter.

🚀 Quick Start

This project demonstrates how to build a LangChain agent that uses the MCP protocol to interact with various services:

Tavily Search: Web search and news search functionality.
Weather: Simulated weather information retrieval.
Math: Mathematical expression calculation.

The agent uses the ReAct agent pattern of LangGraph and dynamically selects and uses these tools based on the user's query.

✨ Features

Graceful Shutdown Mechanism: All MCP servers implement perfect signal handling to ensure clean termination.
Sub - process Management: The main agent tracks and manages all MCP server sub - processes.
Error Handling: The entire application has powerful error - handling capabilities.
Modular Design: Easy to expand and add new MCP servers.

🔧 Technical Details

Graceful Shutdown Mechanism

The project implements a comprehensive graceful shutdown system:

Signal Handling: Captures SIGINT and SIGTERM signals to initiate a graceful shutdown.
Process Tracking: The main agent maintains a registry of all sub - processes.
Clean - up Process: Ensures that all sub - processes are terminated on exit.
Shutdown Flag: Each MCP server has a shutdown flag to prevent new operations during shutdown.
Asynchronous Collaboration: Uses asyncio to allow ongoing operations to complete as much as possible.

📦 Installation

# Clone the repository
git clone https://github.com/yourusername/langchain-mcp.git
cd langchain-mcp

# Create a virtual environment
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# Install dependencies
pip install -e .

📚 Documentation

Configuration

Create a .env file in the project root directory and add the following variables:

OPENAI_API_KEY=Your OpenAI API key
TAVILY_API_KEY=Your Tavily API key

Usage

Run the agent from the command line:

python src/agent.py

The agent will prompt for a query and then process it using appropriate tools.

Development

To add a new MCP server:

Create a new file in src/mcpserver/.
Implement the server with perfect signal handling.
Update src/mcpserver/__init__.py to expose the new server.
Add the new server configuration to src/agent.py.

📄 License

MIT

Featured MCP Services

Duckduckgo MCP Server

Certified

The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.

A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.

The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.

TypeScript

4.3 points

Markdownify MCP

Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.

Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.

UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.

573

5 points

Context7

Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.

The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.

Python

761

4.8 points

Zhiqi Future, Your AI Solution Think Tank

English 简体中文繁體中文にほんご