roy-shivam164/Intacct-MCP-Server-Python

Weather MCP Project Setup

This project provides a weather API and MCP (Model Context Protocol) tools for retrieving weather alerts and forecasts using the National Weather Service (NWS) API.

Prerequisites

• Python 3.9+
• uv (a fast Python package manager and virtual environment tool)

Setup Instructions

1. Clone the Repository

git clone <your-repo-url>
cd Intact-MCP-Python/weather

2. Install uv

If you don't have uv installed, run:

pip install uv

3. Install Dependencies

uv pip install -r requirements.txt

Or, if using a pyproject.toml:

uv pip install -r pyproject.toml

4. Run the Server

To start the FastAPI server (for example, using main.py):

uvicorn main:app --reload

Or, if you have a custom server script:

python main.py

5. Using MCP Tools

The MCP tools are available via the MCP server. To run the MCP server:

python weather.py

Project Structure

• main.py - FastAPI app entry point
• weather.py - MCP tool definitions
• routes.py - (Optional) Additional API routes
• server.py - (Optional) Custom server logic
• pyproject.toml - Project dependencies and metadata

Notes

• Make sure to set your Python interpreter to the virtual environment created by uv.
• The API uses the National Weather Service (NWS) and may require a valid User-Agent header.

Useful Commands

• Install a new package: uv pip install <package>
• Update dependencies: uv pip install -U -r requirements.txt
• Run tests: pytest

---

For more information on uv, see the uv documentation.