GeoFS MCP Server
by lobstercare
- geofs-mcp
- public
index.html•5.96 kB
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>GeoFS MCP Server</title>
<style>
body {
font-family: Arial, sans-serif;
line-height: 1.6;
margin: 0;
padding: 20px;
color: #333;
max-width: 800px;
margin: 0 auto;
}
h1 {
color: #2c3e50;
border-bottom: 2px solid #3498db;
padding-bottom: 10px;
}
h2 {
color: #2980b9;
margin-top: 30px;
}
.bookmarklet {
display: inline-block;
padding: 10px 15px;
background-color: #3498db;
color: white;
text-decoration: none;
border-radius: 4px;
margin: 20px 0;
font-weight: bold;
}
.bookmarklet:hover {
background-color: #2980b9;
}
.instructions {
background-color: #f8f9fa;
border-left: 4px solid #3498db;
padding: 15px;
margin: 20px 0;
}
code {
background-color: #f1f1f1;
padding: 2px 4px;
border-radius: 3px;
font-family: monospace;
}
.warning {
background-color: #fff3cd;
border-left: 4px solid #ffc107;
padding: 15px;
margin: 20px 0;
}
</style>
</head>
<body>
<h1>GeoFS Model Context Protocol (MCP) Server</h1>
<p>This server provides an interface for controlling aircraft in the GeoFS flight simulator using natural language commands through GPT-4o.</p>
<div class="instructions">
<h2>How to Connect to GeoFS</h2>
<p>To connect the MCP server to GeoFS, you have two options:</p>
<h3>Option 1: Use the Bookmarklet (Recommended)</h3>
<p>Drag this link to your bookmarks bar:</p>
<a href="javascript:(function(){const script=document.createElement('script');fetch('http://localhost:3002/direct-control.js').then(response=>response.text()).then(scriptContent=>{const blob=new Blob([scriptContent],{type:'application/javascript'});const url=URL.createObjectURL(blob);script.src=url;document.head.appendChild(script);console.log('GeoFS MCP Control Panel loaded successfully!');}).catch(error=>{console.error('Failed to load GeoFS MCP Control Panel:',error);alert('Failed to load GeoFS MCP Control Panel. Check the console for details.');});})()" class="bookmarklet">GeoFS MCP Control</a>
<p>Then:</p>
<ol>
<li>Open <a href="https://www.geo-fs.com" target="_blank">GeoFS</a> in your browser</li>
<li>Select the Boeing 787-9 Vistara aircraft</li>
<li>Once GeoFS is fully loaded, click the bookmarklet in your bookmarks bar</li>
<li>The MCP control panel should appear in the GeoFS interface</li>
</ol>
<h3>Option 2: Use the Console</h3>
<p>If the bookmarklet doesn't work, you can paste this code in your browser console (F12):</p>
<pre><code>
(function(){
const script = document.createElement('script');
fetch('http://localhost:3002/direct-control.js')
.then(response => response.text())
.then(scriptContent => {
const blob = new Blob([scriptContent], { type: 'application/javascript' });
const url = URL.createObjectURL(blob);
script.src = url;
document.head.appendChild(script);
console.log('GeoFS MCP Control Panel loaded successfully!');
})
.catch(error => {
console.error('Failed to load GeoFS MCP Control Panel:', error);
alert('Failed to load GeoFS MCP Control Panel. Check the console for details.');
});
})();
</code></pre>
</div>
<h2>Using GPT-4o to Control Your Aircraft</h2>
<p>Once the control panel is loaded in GeoFS:</p>
<ol>
<li>Click on the "GPT Control" tab in the control panel</li>
<li>Enter a natural language command in the text area (e.g., "Take off from runway 3 at Luxembourg airport")</li>
<li>Click "Send to GPT" to execute the command</li>
<li>The GPT response will appear below, and the aircraft will begin executing the commands</li>
</ol>
<h3>Example Commands</h3>
<ul>
<li>"Take off from the current runway with flaps at 30%"</li>
<li>"Turn right to heading 180 degrees"</li>
<li>"Begin approach to the nearest runway"</li>
<li>"Execute a holding pattern at current altitude"</li>
<li>"Land at the current airport"</li>
</ul>
<div class="warning">
<h3>Important Notes</h3>
<p>For full OpenAI GPT-4o integration, you'll need to add your OpenAI API key in the settings section of the GPT Control tab. Without an API key, the system will use simulated responses for common flight commands.</p>
<p>Make sure the MCP server is running on port 3002 before attempting to connect.</p>
</div>
<h2>Server Status</h2>
<p>The server is currently running on <a href="http://localhost:3002">http://localhost:3002</a>.</p>
<p>API endpoints:</p>
<ul>
<li><code>/api/status</code> - Get server status</li>
<li><code>/gpt-command</code> - Send commands to GPT-4o</li>
</ul>
<footer style="margin-top: 50px; border-top: 1px solid #eee; padding-top: 20px; color: #777;">
<p>GeoFS MCP Server - Powered by Model Context Protocol</p>
</footer>
<script>
// Check if server is running
fetch('/api/status')
.then(response => response.json())
.then(data => {
console.log('Server status:', data);
})
.catch(error => {
console.error('Error checking server status:', error);
});
</script>
</body>
</html>
Latest Blog Posts
- MCP Moves to the Linux Foundation: Neutral Stewardship for Agentic InfrastructureBy Om-Shree-0709 on .mcpanthropicLinux Foundation
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/lobstercare/geofs-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server