My MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@My MCP Serverwhat's the weather in Tokyo?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
My MCP Server
A lightweight Model Context Protocol (MCP) server built with FastMCP, exposing three tools that can be used by any MCP-compatible client (Claude Desktop, agents, etc.).
Tools
Tool | Description | Input |
| Adds two integers together |
|
| Returns the current date and time as an ISO string | none |
| Fetches a 3-day weather forecast for any city via wttr.in |
|
Related MCP server: MCP Playground Server
Demo
Weather forecast for Addis Ababa fetched live via the get_current_weather tool:

Tech Stack
Python 3.12
FastMCP — MCP server framework
wttr.in — free weather API (no key required)
uv — package and environment management
Getting Started
1. Clone the repo:
git clone https://github.com/aarongeb/mcp.git
cd mcp2. Create a virtual environment and install dependencies:
uv venv --python 3.12
source .venv/bin/activate
uv sync3. Set up environment variables:
.env
# set MCP_PORT in .env (default: 3000)4. Run the server:
./server.pyThe server starts on http://127.0.0.1:3000 (SSE transport).
Environment Variables
Variable | Description | Default |
| Port the server listens on |
|
Testing the Tools
With the FastMCP test client:
import asyncio
from fastmcp import Client
async def main():
async with Client("http://127.0.0.1:3000/sse") as client:
tools = await client.list_tools()
print("Tools:", [t.name for t in tools])
result = await client.call_tool("add", {"a": 5, "b": 3})
print("add(5,3):", result.content[0].text)
result = await client.call_tool("get_current_time", {})
print("time:", result.content[0].text)
result = await client.call_tool("get_current_weather", {"city": "Addis Ababa"})
print("weather:", result.content[0].text)
asyncio.run(main())uv run test_server.pyWith MCP Inspector (visual UI):
npx @modelcontextprotocol/inspector http://127.0.0.1:3000/sseConnecting to Claude Desktop
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"my-mcp-server": {
"url": "http://127.0.0.1:3000/sse"
}
}
}The server must be running before you open Claude Desktop.
Project Structure
mcp/
├── server.py
├── test_server.py
├── assets/
│ └── weather_demo.png
├── .env
├── .gitignore
└── pyproject.tomlLicense
For personal use.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/aaronGeb/mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server