MCP Agents
Provides FastMCP-based servers with various tools for AI assistants including math operations, file management, note-taking, todo management, and database operations. Offers both basic and advanced server configurations with tools, resources, and prompt templates.
README
MCP Agents - Example FastMCP Server
A simple Model Context Protocol (MCP) server built with FastMCP that demonstrates basic tool implementation.
Features
- greet: Greet a user by name
Installation
This project uses uv for package management and just for task running. Make sure you have both installed:
# Install uv if you don't have it
curl -LsSf https://astral.sh/uv/install.sh | sh
# Install just if you don't have it
# On macOS with Homebrew:
brew install just
# Or with cargo:
cargo install just
Then build the project:
just build
Usage
Running the MCP Server
To start the MCP agents server:
just run
Using with MCP Clients
You can use this server with any MCP-compatible client. The configuration depends on how you want to run the server:
Option 1: Local Development (using source code)
For development or when running from a local clone:
{
"mcpServers": {
"mcp-agents": {
"command": "uv",
"args": ["run", "mcp-agents"],
"cwd": "/Users/means/repository/mcp-agents",
"env": {}
}
}
}
Option 2: PyPI Installation (recommended for end users)
Once published to PyPI, users can use this simpler configuration:
{
"mcpServers": {
"mcp-agents": {
"command": "uvx",
"args": ["amajakai14_mcp-agents"]
}
}
}
Alternative with pipx:
{
"mcpServers": {
"mcp-agents": {
"command": "pipx",
"args": ["run", "amajakai14_mcp-agents"]
}
}
}
Option 3: Version Pinning
To pin to a specific version:
{
"mcpServers": {
"mcp-agents": {
"command": "uvx",
"args": ["amajakai14_mcp-agents==0.1.0"]
}
}
}
For Claude Desktop
Add any of the above configurations to your Claude Desktop config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%/Claude/claude_desktop_config.json
Testing the Tools
Run the test script to verify the tools work correctly:
just test
Available Tools
greet
Greets a user by name.
Parameters:
name(string): The name of the person to greet
Returns: A friendly greeting message.
Example:
{
"name": "greet",
"arguments": {
"name": "Alice"
}
}
Response:
"Hello, Alice!"
Development
Available Just Commands
just build- Install dependencies and sync the projectjust run- Start the MCP agents serverjust test- Run the test scriptjust format- Format code with black and isortjust typecheck- Run type checking with mypyjust dev- Install development dependenciesjust dist- Build distribution packagesjust clean- Clean build artifactsjust publish- Publish to PyPI (used in CI)
Project Structure
mcp-agents/
├── src/
│ └── agents/
│ └── __init__.py # Main MCP server implementation
├── pyproject.toml # Project configuration and dependencies
├── justfile # Task runner configuration
├── mcp_config.json # MCP client configuration example
├── test_tools.py # Simple test script
└── README.md # This file
Adding New Tools
To add new tools using FastMCP:
-
Add a new function with the
@mcp.tool()decorator:@mcp.tool("tool_name", description="Description of what the tool does") def tool_name(param1: type, param2: type) -> return_type: # Tool implementation return result -
Update the README with documentation for the new tool
Running Tests
just test
License
MIT License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.