GeoFS Flight Simulator MCP server

Enables natural language control of aircraft in the GeoFS flight simulator through a WebSocket server that translates commands into simulator actions for takeoff, landing, and navigation maneuvers.
Back to servers
Provider
lobstercare
Release date
Mar 30, 2025
Language
TypeScript
Stats
1 star

The GeoFS MCP Server allows AI models to control and interact with aircraft in the GeoFS browser-based flight simulator through the Model Context Protocol. It provides a bridge between AI systems and the simulator, enabling automated flight control and data retrieval in real-time.

Prerequisites

  • Node.js (v14 or higher)
  • npm or yarn
  • A modern web browser (Chrome recommended)

Installation

  1. Clone the repository:

    git clone https://github.com/yourusername/geofs-mcp-server.git
    cd geofs-mcp-server
    
  2. Install dependencies:

    npm install
    
  3. Build the project:

    npm run build
    

Usage

Starting the Server

Start the MCP server with:

npm start

When started, the server will:

  • Launch a browser window that navigates to GeoFS
  • Wait for GeoFS to fully load before accepting commands
  • Possibly require you to log in to GeoFS if needed

Once running, the server will be available at:

API Endpoints

The server provides several HTTP endpoints:

  • GET /mcp - Get server capabilities and available endpoints
  • GET /mcp/aircraft - Get current aircraft data
  • POST /mcp/aircraft - Control aircraft parameters
  • GET /mcp/flight-data - Get comprehensive flight data
  • POST /mcp/navigation - Set navigation parameters
  • GET /mcp/simulation - Get simulation status
  • POST /mcp/simulation - Control simulation parameters

WebSocket Commands

For real-time communication, use WebSocket connections:

// Example WebSocket message
{
  "id": 1,
  "type": "command",
  "command": "setThrottle",
  "params": {
    "value": 0.75
  }
}

Available commands include:

  • setThrottle - Set engine throttle (0-1)
  • setHeading - Set target heading in degrees
  • getPosition - Get current aircraft position
  • selectAircraft - Change to a different aircraft
  • takeOff - Execute takeoff procedure
  • land - Execute landing procedure
  • getFlightData - Get comprehensive flight data

Example Client

The repository includes example client code. Run it with:

node examples/simple-client.js

How It Works

The GeoFS MCP server uses Puppeteer to control a browser instance running GeoFS. It provides a standardized MCP interface that allows AI models to interact with the flight simulator through HTTP and WebSocket APIs, enabling:

  • Control of aircraft flight parameters (throttle, heading, etc.)
  • Access to real-time flight data (position, speed, attitude)
  • Navigation between waypoints and airports
  • Selection of different aircraft models
  • Execution of flight maneuvers (takeoff, landing)

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later