Automated publishing workflow for deploying the MCP server package to PyPI when releases are created
Package distribution platform for publishing and installing the MCP server package
Database management capabilities including creating tables and managing database structures through the advanced server's tools
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:
Then build the project:
Usage
Running the MCP Server
To start the MCP agents server:
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:
Option 2: PyPI Installation (recommended for end users)
Once published to PyPI, users can use this simpler configuration:
Alternative with pipx
:
Option 3: Version Pinning
To pin to a specific version:
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:
Available Tools
greet
Greets a user by name.
Parameters:
name
(string): The name of the person to greet
Returns: A friendly greeting message.
Example:
Response:
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
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 resultUpdate the README with documentation for the new tool
Running Tests
License
MIT License
This server cannot be installed
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
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.