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., "@Weather MCP Serverwhat's the forecast for New York this weekend?"
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.
Setup & Run (concise)
Clone & install
git clone https://github.com/JessiP23/mcp.git
cd mcp/weather
# Python venv
python -m venv .venv
source .venv/bin/activate
pip install -U pip
Install uv (runtime)
macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# restart terminal after install
Windows (PowerShell)
iwr -useb https://astral.sh/uv/install.ps1 | iex
# restart shell after install
Create project with uv (optional)
uv init weather
cd weather
uv venv
source .venv/bin/activate
uv add "mcp[cli]" httpx
touch weather.py
Run
Install Inspector (if needed):
npx @modelcontextprotocol/inspector@latest --version
Run the MCP server via Inspector:
npx @modelcontextprotocol/inspector uv --directory /Users/jessipavia/mcp/weather run python main.py
(Optional) Run manual search locally:
python main.py --manual
Test files (concise)
Copy a local file into
samples/:
cp /path/to/local/file.txt samples/
Download an online file into
samples/:
curl -L "https://example.com/file.txt" -o samples/file.txt