adsb-mcp-server
Exposes real-time ADS-B aircraft data from a feeder, enabling natural language queries for aircraft positions, receiver statistics, and flight searches.
README
ADS-B MCP Server
A Model Context Protocol (MCP) server that exposes the data of a typical ADS-B feeder instance for use from within Claude (and possibly other LLMs).
This was initially written in order to provide an MCP server connected to the <a href="https://github.com/dirkhh/adsb-feeder-image">ADS-B Feeder Image</a> running an Ultrafeeder container - but it will work with any feeder that is providing the APIs typically associated with readsb / tar1090.
Features
This MCP server so far provides access to:
- Aircraft Data: Real-time aircraft positions, callsigns, altitudes, and tracking information plus optionally (where available) route information for commercial flights
- Receiver Statistics: Performance metrics, message counts, and system status
- Search Functionality: Find specific aircraft by callsign, hex code, or flight number
- Range Statistics: Coverage area and signal range information
Installation
Prerequisites
- Node.js 18.0 or higher
- npm (comes with Node.js)
- Access to an ADS-B feeder
Install Dependencies
# Clone the repository
git clone https://github.com/dirkhh/adsb-mcp-server.git
cd adsb-mcp-server
# Install dependencies
npm install
# Build the project
npm run build
MCP Client Setup Guide
This guide will help you connect various MCP clients to your ADS-B MCP server.
Prerequisites
- Running ADS-B Feeder: Make sure your ADS-B feeder is running and accessible - the easiest way to do that may be running the ADS-B Feeder Image
- Python MCP Server: The readsb MCP server should be working
- Network Access: Client needs access to your feeder's API endpoints
Option 1: Claude Desktop (Recommended)
Step 1: Configure Claude Desktop
Recommended: Use the automatic setup script:
npm run build
node dist/setup_remote_config.js
This script will:
- Prompt you for your ADS-B feeder host and port
- Automatically create the correct configuration
- Merge with existing Claude Desktop configuration if present
- Provide clear instructions for next steps
Step 2: Restart Claude Desktop (or Reload MCP Configuration if your version of Claude Desktop supports that)
Close and reopen Claude Desktop to load the new configuration. As of this writing, not all versions of Claude have an option to reload its configuration.
Step 3: Test the Connection
In Claude Desktop, try asking:
- "What are the 5 closest planes to my feeder?"
- "Show me aircraft to the east of my location"
Option 2: MCP Inspector
Install MCP Inspector
npm install -g @modelcontextprotocol/inspector
Run with ADS-B MCP server
npm run build
npx @modelcontextprotocol/inspector node dist/src/readsb_mcp_server.js --base-url http://adsb-feeder.local
This will open a web interface where you can test the MCP server tools.
Creating MCP Bundles
You can create an MCP Bundle (.mcpb file) for easy distribution using the official MCPB tool:
# Install the official MCPB tool (Node.js required)
npm install -g @anthropic-ai/mcpb
# Build the project
npm run build
# Create bundle using official tool
mcpb pack .
The bundle will be created as adsb-mcp-server.mcpb and can be distributed and installed in MCP-compatible clients. The bundle includes all Node.js dependencies for self-contained operation.
Option 3: Custom Node.js Client
Use the included simple MCP client:
npm run build
node dist/test/remote_mcp_client.js
This provides an interactive command-line interface to test all the MCP tools.
Option 4: Test Script
Run the basic connection test:
npm run build
node dist/test/test_remote_connection.js
This will verify that the ADS-B MCP server is working correctly.
Configuration Options
Base URL Configuration
Adjust the --base-url parameter based on your setup:
- Typical ADS-B Feeder Image: (by default
adsb-feeder.localis used as host) - Feeder with known IP address
--base-url http://192.168.123.45 - Local feeder running on this system:
--base-url http://localhost - Running in a container in the ADS-B Feeder Image adsb_im_bridge Docker network:
--base-url http://ultrafeeder
Port Configuration
The server connects to these readsb endpoints:
- Port 8080: REST API (
/data/aircraft.json,/data/stats.json)
Make sure these ports are accessible from your MCP client. If your tar1090 runs on a different port, adjust the command line accordingly, e.g. --base-url http://100.99.98.97:6543
Troubleshooting
Connection Issues
- Check if you can manually get to the ADS-B data:
curl http://adsb-feeder.local:8080/data/aircraft.json
Claude configuration issues
- Check the Claude MCP logs:
e.g., ~/Library/Logs/Claude/mcp-server-readsb.log on macOS
Performance Issues
- Limit result counts to avoid overwhelming responses
- Use distance filters to reduce data processing
- Monitor memory usage for large aircraft datasets
Example Queries
Once connected, you can ask natural language questions like:
- "What are the 5 closest aircraft to my feeder?"
- "Show me all planes to the east within 50 miles"
- "Are there any aircraft to the north?"
- "What's the closest plane to the south?"
- "Find aircraft in the northeast quadrant"
- "Search for flight UAL123"
- "Show me receiver statistics"
Advanced Configuration
Custom Auto-Approval
Configure which tools require approval:
{
"autoApprove": [
"get_aircraft_data",
"get_receiver_stats"
]
}
Tools not in autoApprove will require manual approval in Claude Desktop.
Support
If you encounter issues:
- Reach out in the #adsb-dot-im channel on the <a href="https://discord.gg/7buWAFA28H">SDR Enthusiasts Discord</a>
License
This project contains some AI generated code (with potentially questionable IP issues); overall the project is licensed under the GPLv3.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.