MCP-YNU - FastMCP Server
A dynamic MCP server implementation using FastMCP that automatically loads tools, resources, and prompts from respective directories.
Features
- Dynamic loading of modules from
tools/,resources/, andprompts/directories - Automatic discovery and registration of modules
- Simple configuration and extensibility
- Type hints for better code clarity and static analysis
- Comprehensive logging for monitoring server activity
Recent Updates
- Added type hints throughout the codebase
- Improved MCP instance handling
- Added logging functionality
- Added MIT license
- Updated documentation with reference links
Directory Structure
mcp-ynu/
├── tools/ # Directory for tool modules
│ ├── __init__.py
│ ├── example.py
├── resources/ # Directory for resource modules
│ ├── __init__.py
│ ├── example.py
├── prompts/ # Directory for prompt modules
│ ├── __init__.py
│ ├── example.py
├── logger.py # Logger implementation
├── main.py # Main implementation
├── mcp_server.py # MCP server implementation
├── README.md # Project documentation
├── LICENSE # MIT License
└── pyproject.toml # Project configuration
Usage
- Create modules in the appropriate directories
- Import mcp via
from mcp_server import mcp - Run the server:
python main.py
Example Modules
Tools Module Example (tools/example.py)
from mcp_server import mcp
import httpx
@mcp.tool()
def calculate_bmi(weight_kg: float, height_m: float) -> float:
"""Calculate BMI given weight in kg and height in meters"""
return weight_kg / (height_m**2)
@mcp.tool()
async def fetch_weather(city: str) -> str:
"""Fetch current weather for a city"""
async with httpx.AsyncClient() as client:
response = await client.get(f"https://api.weather.com/{city}")
return response.text
Resources Module Example (resources/example.py)
from mcp_server import mcp
@mcp.resource("config://app")
def get_config() -> str:
"""Static configuration data"""
return "App configuration here"
@mcp.resource("users://{user_id}/profile")
def get_user_profile(user_id: str) -> str:
"""Dynamic user data"""
return f"Profile data for user {user_id}"
Prompts Module Example (prompts/example.py)
from mcp_server import mcp
from mcp.server.fastmcp.prompts import base
@mcp.prompt()
def review_code(code: str) -> str:
return f"Please review this code:nn{code}"
@mcp.prompt()
def debug_error(error: str) -> list[base.Message]:
return [
base.UserMessage("I'm seeing this error:"),
base.UserMessage(error),
base.AssistantMessage("I'll help debug that. What have you tried so far?"),
]
Debugging
- Update
MCP_TRANSPORT_TYPEin.env, Executepython main.pyto start the mcp server - Execute
npx @modelcontextprotocol/inspectorto open the inspect. - Choose
SSETransport Type with URLhttp://localhost:<mcp_server_port>/sseor ChooseSTDIOTransport Type with Commandpythonand Arguments/path/to/main.py

Requirements
- Python >= 3.10
- FastMCP
Reference Links
- MCP Python SDK Documentation
- MCP Core Concepts
- FastMCP Implementation
License
This project is licensed under the MIT License - see the LICENSE file for details.
MCP-YNU FastMCP Server
Project Details
- ynu/mcp-ynu
- MIT License
- Last Updated: 4/2/2025
Recomended MCP Servers
Agile Kanban board backed by SQLite and exposed via the Model Context Protocol (MCP). Lets LLMs read, comment...
A free MCP server to analyze and extract insights from public filings, earnings transcripts, financial metrics, stock market...
A model context protocol server for Jira API
A Model Context Protocol server that integrates AI assistants with Metabase analytics platform
An MCP server implementation that provides tools for interacting with the [Telegram Bot API](https://core.telegram.org/bots/api).
Basic Memory is a knowledge management system that allows you to build a persistent semantic graph from conversations...
Model Context Protocol Servers
Model Context Protocol (MCP) server for the Zotero API, in Python
本地部署的MySql MCP服务





