Supports containerized deployment through Docker, enabling portable setup of the AetherLink server with all dependencies included.
Provides testing infrastructure for verifying functionality of radio protocol decoders and hardware interfaces.
Built on Python 3.10+, allowing for extensible development of new radio protocol decoders and hardware support.
Click on "Install 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., "@AetherLink SDR MCPscan 100-150 MHz for emergency services signals"
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.
AetherLink-SDR-MCP: Software Defined Radio Model Context Protocol Server
Control Software Defined Radios and decode radio protocols through an AI-friendly Model Context Protocol interface.
🚀 Features
Protocol Decoders: ADS-B aircraft tracking, POCSAG pagers, AIS ship tracking, Meteor-M LRPT satellites, ISM band devices
Weather Satellites: Meteor-M2-3/M2-4 LRPT decoding with SatDump (NOAA APT deprecated - decommissioned Aug 2025)
Advanced Analysis: Real-time spectrum analysis, waterfall displays, signal detection, frequency scanning
Audio Recording: Demodulate and record FM/AM audio as WAV files
ISM Band Scanning: Decode 433MHz/315MHz devices (weather stations, sensors, doorbells, tire pressure monitors)
MCP Integration: Seamless integration with Claude Desktop and other MCP clients
27 MCP Tools: Complete SDR control through natural language
Related MCP server: MCP Hardware Access Library
📦 Installation
Prerequisites
1. RTL-SDR Drivers:
2. RTL-SDR Tools:
3. SatDump for Meteor-M LRPT decoding (required for weather satellites):
4. rtl_433 for ISM band decoding (optional but recommended):
5. POCSAG Decoder (optional):
5. Python 3.10+
Install from Source
Required Python Packages
The following are installed automatically:
pyrtlsdr- RTL-SDR hardware interfacenumpy- Signal processingscipy- Filtering and demodulationmcp- Model Context Protocol serverPillow- Image processing for NOAA satellite imagespyModeS- ADS-B decoding (optional)
🎯 Quick Start
1. Configure Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or equivalent:
Important: Use absolute paths for the Python interpreter.
2. Restart Claude Desktop
Quit and restart Claude Desktop to load the MCP server.
3. Test the Connection
In Claude Desktop:
You should see: "Successfully connected to RTL-SDR"
📡 Supported Hardware
Device | RX Frequency | TX Support | Status | Tested |
RTL-SDR | 24 MHz - 1766 MHz | ❌ | ✅ Stable | ✅ Yes |
HackRF One | 1 MHz - 6 GHz | ✅ | ✅ Working | ⚠️ Limited |
Nooelec E4000 | 55 MHz - 2300 MHz | ❌ | ✅ Stable | ✅ Yes |
📊 Protocol Support
Protocol | Description | Status |
ADS-B | Aircraft tracking | ✅ Ready |
POCSAG | Pager decoding | ✅ Ready |
AIS | Ship tracking | ✅ Ready |
Meteor-M LRPT | Weather satellites (M2-3, M2-4) | ✅ Ready |
NOAA APT | Weather satellites (DEPRECATED) | ⚠️ EOL Aug 2025 |
ISM Band | 433MHz/315MHz devices | ✅ Ready |
Protocol Details
ADS-B (1090 MHz):
Uses
rtl_adsbsubprocess for demodulationpyModeS for message decoding
Tracks aircraft position, speed, altitude, callsign
FULLY TESTED AND WORKING
POCSAG (152/454/929 MHz):
Uses
multimon-ngfor professional decodingSupports 512/1200/2400 baud
Alphanumeric and numeric messages
Common frequencies: 152.240 MHz, 454 MHz, 929-931 MHz
AIS (161.975/162.025 MHz):
GMSK demodulation (simplified)
Decodes ship position, speed, type
Requires coastal location
Meteor-M LRPT (137 MHz):
Uses
satdumpsubprocess for OQPSK demodulationDigital LRPT transmission with error correction
Decodes visible and infrared channels
Active satellites: Meteor-M2-3 (137.9 MHz), Meteor-M2-4 (137.9 MHz primary, 137.1 MHz backup)
CURRENT WEATHER SATELLITE STANDARD (replaced NOAA APT)
NOAA APT (137 MHz) - DEPRECATED:
AM demodulation (analog)
All NOAA APT satellites decommissioned August 2025
Tool remains for historical/testing purposes
⚠️ Use Meteor-M LRPT for current weather satellite imaging
ISM Band (433/315/868/915 MHz):
Uses
rtl_433subprocess for decodingMulti-frequency hopping support
Decodes 200+ device types automatically
Weather stations, sensors, doorbells, tire pressure monitors, remote controls
Common frequencies: 433.92 MHz (EU/Asia), 315 MHz (NA), 868 MHz (EU), 915 MHz (NA)
🛠️ Available MCP Tools (27 Total)
Core SDR Control (5 tools)
sdr_connect- Connect to RTL-SDR or HackRFsdr_disconnect- Disconnect from SDRsdr_set_frequency- Set center frequency in Hzsdr_set_gain- Set gain (dB or 'auto')sdr_get_status- Get hardware status
Aviation (3 tools)
aviation_track_aircraft- Start ADS-B tracking on 1090 MHzaviation_stop_tracking- Stop trackingaviation_get_aircraft- Get list of tracked aircraft
Pager Decoding (3 tools)
pager_start_decoding- Start POCSAG decoderpager_stop_decoding- Stop decodingpager_get_messages- Get decoded messages
Marine (3 tools)
marine_track_vessels- Start AIS ship trackingmarine_stop_tracking- Stop trackingmarine_get_vessels- Get vessel list
Weather Satellites (2 tools)
satellite_decode_meteor- Decode Meteor-M2-3/M2-4 LRPT satellite pass (CURRENT)satellite_decode_noaa- Decode NOAA APT satellite pass (DEPRECATED - satellites decommissioned)
ISM Band Devices (3 tools)
ism_start_scanning- Start scanning ISM bands (433/315/868/915 MHz) with multi-frequency hoppingism_stop_scanning- Stop ISM band scanningism_get_devices- Get detected devices (weather stations, sensors, etc.)
Analysis (5 tools)
spectrum_analyze- Analyze RF spectrum (FFT, signal detection)spectrum_scan- Scan frequency rangerecording_start/recording_stop- Record raw IQ samples (saved to/tmp/sdr_recordings/)audio_record_start/audio_record_stop- Record demodulated audio as WAV (FM/AM)
HackRF Transmit (2 tools)
hackrf_set_tx_gain- Set transmit gainsignal_generator- Generate and transmit signals
📖 Usage Examples
Track Aircraft
After 30-60 seconds:
Decode Pagers
Wait a few minutes, then:
Note: Check RadioReference.com for active pager frequencies in your area.
Analyze Spectrum
Scan for Signals
Record Audio from FM Radio
Wait for desired duration (e.g., 30 seconds), then:
Files saved to: /tmp/sdr_recordings/audio_YYYYMMDD_HHMMSS_XXXMHz_FM.wav
Record Raw IQ Samples
Wait for desired duration, then:
Files saved to: /tmp/sdr_recordings/recording_YYYYMMDD_HHMMSS_XXXMHz.iq
Use case: Advanced analysis, replay, or processing with GNU Radio/SDR#
Meteor-M Weather Satellite (when overhead)
Requirements:
SatDump installed (
brew install satdump)Satellite pass overhead (use tools like Gpredict, N2YO, or Heavens-Above to predict passes)
Ideally a V-dipole antenna tuned for 137 MHz
What you get:
Visible light channel images
Infrared channel images
Composite RGB images
Saved to
/tmp/sdr_recordings/meteor_METEOR-M2-4_*/
Tips:
Meteor-M2-4 transmits on 137.9 MHz (primary) or 137.1 MHz (backup)
Best results with satellite elevation >30°
Full pass is typically 10-15 minutes
Use higher gain (40-49 dB) for weak signals
NOAA Satellite - DEPRECATED
⚠️ Note: All NOAA APT satellites were decommissioned in August 2025. This tool remains for historical purposes only. Use satellite_decode_meteor for current weather satellite imaging.
Scan ISM Band Devices
Wait 1-2 minutes for devices to transmit, then:
Common devices detected:
Weather stations (temperature, humidity, wind, rain)
Wireless thermometers
Tire pressure monitoring systems (TPMS)
Door/window sensors
Doorbells and remote controls
Soil moisture sensors
Tips:
Weather stations typically transmit every 30-60 seconds
433.92 MHz is common in Europe/Asia
315 MHz is common in North America
Try different frequency combinations:
[433.92, 315]or[868, 915]Increase hop interval for more dwell time per frequency
🔧 Development
Project Structure
Architecture
Device Management:
RTL-SDR and subprocess decoders use exclusive device access
Python SDR control and subprocess tools (rtl_adsb, rtl_433) cannot run simultaneously
Subprocess-based decoders automatically disconnect Python SDR
Stopping decoder reconnects Python SDR control
Decoders:
ADS-B:
rtl_adsbsubprocess + pyModeSISM Band:
rtl_433subprocess with JSON output + multi-frequency hoppingPOCSAG:
rtl_fm+multimon-ngpipelineAIS: Built-in GMSK demodulator (simplified)
NOAA: Built-in AM demodulator + sync detection