GeoFS MCP Server
Enables control and interaction with aircraft in the GeoFS browser-based flight simulator, allowing for setting flight parameters, retrieving real-time flight data, navigating between waypoints, and executing flight maneuvers through JavaScript APIs.
Powers the MCP server that bridges AI models with the GeoFS flight simulator, providing HTTP and WebSocket endpoints for aircraft control, flight data retrieval, and simulation management.
Used to programmatically control a browser instance running the GeoFS flight simulator, enabling automated interaction with the simulation environment.
Click on "Deploy 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., "@GeoFS MCP Servertake off from JFK and fly to LAX at cruising altitude"
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.
GeoFS MCP Server
A Model Context Protocol (MCP) server for the GeoFS flight simulator, allowing AI models to control and interact with aircraft in the GeoFS browser-based flight simulator.
Features
π« Control aircraft flight parameters (throttle, heading, etc.)
π Access real-time flight data (position, speed, attitude)
πΊοΈ Navigate between waypoints and airports
βοΈ Select different aircraft models
π Execute flight maneuvers (takeoff, landing)
Related MCP server: TAK Server MCP
Prerequisites
Node.js (v14 or higher)
npm or yarn
A modern web browser (Chrome recommended)
Installation
Clone this repository:
git clone https://github.com/yourusername/geofs-mcp-server.git cd geofs-mcp-serverInstall dependencies:
npm installBuild the project:
npm run build
Usage
Starting the Server
Start the MCP server:
npm startThe server will launch a browser window that navigates to GeoFS
You may need to log in to GeoFS if required
The server will wait for GeoFS to fully load before accepting commands
The MCP server will be available at:
HTTP:
http://localhost:3000WebSocket:
ws://localhost:3000
Using with AI Models
This MCP server can be used with AI models that support the Model Context Protocol, allowing them to:
Control aircraft in the simulator
Retrieve flight data and simulator state
Execute complex flight maneuvers
Plan and follow flight routes
API Endpoints
GET /mcp- Get server capabilities and available endpointsGET /mcp/aircraft- Get current aircraft dataPOST /mcp/aircraft- Control aircraft parametersGET /mcp/flight-data- Get comprehensive flight dataPOST /mcp/navigation- Set navigation parametersGET /mcp/simulation- Get simulation statusPOST /mcp/simulation- Control simulation parameters
WebSocket Commands
The server also supports WebSocket for real-time communication:
// Example WebSocket message
{
"id": 1,
"type": "command",
"command": "setThrottle",
"params": {
"value": 0.75
}
}Available commands:
setThrottle- Set engine throttle (0-1)setHeading- Set target heading in degreesgetPosition- Get current aircraft positionselectAircraft- Change to a different aircrafttakeOff- Execute takeoff procedureland- Execute landing proceduregetFlightData- Get comprehensive flight data
Example Client
See the examples/simple-client.js file for a basic example of how to connect to and use the GeoFS MCP server.
To run the example:
node examples/simple-client.jsHow 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.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgements
GeoFS - The browser-based flight simulator
Model Context Protocol - Protocol specification for AI model context
This server cannot be deployed
Maintenance
Related MCP Connectors
Geo-based flight search MCP server. Find more flights between any two places on earth
Geospatial AI MCP server β satellite imagery, embeddings, weather, GNS governance
Search and compare flight offers through a cache-aware Streamable HTTP MCP server for AI agents.
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceA server that enables AI assistants to control a browser through tools, allowing them to perform web automation tasks like navigation, typing, clicking, and taking screenshots.-
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that integrates TAK Server with AI systems, providing geospatial-aware tools for querying, analyzing, and interacting with tactical data.10MIT
- AlicenseAqualityCmaintenanceMCP server giving AI agents access to real-time aviation data β live flight tracking, airport weather, airline and airport information.103MIT
- FlicenseNot gradedqualityBmaintenanceProvides the JSBSim flight-dynamics engine as an MCP service, enabling AI agents to control and simulate aircraft in real-time through natural language.-