MyMCP

A collection of Model Context Protocol (MCP) servers providing various integrations and capabilities for MCP-compatible clients like Claude Desktop, VS Code, and other AI applications.

Overview

This repository contains multiple MCP servers, each designed to extend the capabilities of AI assistants through the Model Context Protocol. Each server is independently deployable and provides specific functionality through a standardized interface.

Available Servers

🪝 mcp-server-webhooker

A webhook integration server that enables sending messages to various webhook services.

Features:

Discord webhook integration
Google Chat webhook integration
Robust error handling
Built with FastMCP framework

Tools:

send_discord_message - Send messages to Discord channels
send_google_chat_message - Send messages to Google Chat spaces

🔍 mcp-server-websearch

A web search server that provides internet search capabilities using OpenAI's web search functionality.

Features:

Web search using OpenAI API
Environment-based configuration
FastMCP framework integration

Tools:

web_search - Perform web searches and return results

Prerequisites

Python 3.13 or higher
uv package manager (recommended)
OpenAI API key (for websearch server)

Quick Start

1. Clone the Repository

git clone https://github.com/yourusername/MyMCP.git
cd MyMCP

2. Choose a Server

Navigate to the specific server directory you want to use:

# For webhook functionality
cd mcp-server-webhooker

# For web search functionality
cd mcp-server-websearch

3. Install Dependencies

Using uv (recommended):

uv sync

4. Configure (if needed)

For the websearch server, create a .env file:

echo "OPENAI_API_KEY=your_openai_api_key_here" > .env

5. Run the Server

uv run main.py

Usage with MCP Clients

Claude Desktop

Add the server configuration to your Claude Desktop MCP settings:

{
  "mcpServers": {
    "webhooker": {
      "command": "uv",
      "args": ["run", "/path/to/MyMCP/mcp-server-webhooker/main.py"],
      "cwd": "/path/to/MyMCP/mcp-server-webhooker"
    },
    "websearch": {
      "command": "uv",
      "args": ["run", "/path/to/MyMCP/mcp-server-websearch/main.py"],
      "cwd": "/path/to/MyMCP/mcp-server-websearch",
      "env": {
        "OPENAI_API_KEY": "your_openai_api_key_here"
      }
    }
  }
}

VS Code with MCP Extension

Configure the servers in your VS Code MCP extension settings, pointing to the respective server directories and main.py files.

Development

Each server is built using the FastMCP framework, which provides:

Easy tool registration with decorators
Automatic schema generation
Built-in error handling
Standard MCP protocol compliance

Adding New Servers

Create a new directory following the naming convention mcp-server-{name}
Initialize with a pyproject.toml and main.py
Use FastMCP to build your server
Add documentation in a README.md
Update this main README with your server information

Contributing

Fork the repository
Create a feature branch
Make your changes
Add tests if applicable
Submit a pull request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Related Resources

Support

For issues and questions:

Open an issue in this repository
Check individual server README files for specific documentation
Refer to the MCP community resources

my-dev-mcp