FastMCP Demo

Provides a production-ready FastMCP reference endpoint with local, Docker, and remote deployment options.

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "apoojary94-mcp_hackathon": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-v",
        "$(pwd)\":/app",
        "mcp-demo"
      ]
    }
  }
}

You can run a production-ready MCP server based on FastMCP locally, in Docker, or remotely via a provided MCP URL. This server lets Cursor load an MCP endpoint for interactive prompts and automation, with practical start workflows and clear deployment options.

How to use

You use an MCP client to connect to the server and start interacting with prompts and responses. Depending on your setup, you can load the MCP locally through Python, run it in Docker for isolation, or connect to a remote MCP endpoint. The server supports standard MCP workflows you would expect from a fast, hackathon-ready reference server.

How to install

Prerequisites you need before you begin.

Local Python setup requires Python 3.12 or newer and uv. You can also install Docker and Node.js if you plan to use Docker or run remote MCPs.

Local Python Setup

uv sync
uv run server.py

Docker Setup

# Build the image
docker build -t mcp-demo:latest .

# Run the container
docker run --rm -i mcp-demo:latest

# Development mode with live reload
docker run --rm -it -v "$(pwd)":/app mcp-demo:latest

Remote MCP (no local setup)

npx -y mcp-remote https://cursor-denver-mcp-hackathon.fastmcp.app/mcp