aprs-mcp
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., "@aprs-mcp send an APRS message to ZL1ABC saying hello"
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.
aprs-mcp
Model Context Protocol (MCP) server exposing the APRS-IS network as tools for
any LLM agent (opencode, Claude Desktop, Cursor, Windsurf, generic MCP
clients). Built on aprslib and fastmcp.
APRS transmissions are public. Only transmit with a valid amateur-radio callsign and in accordance with the rules that apply in your jurisdiction.
Tools
Tool | Purpose |
| List the APRS commands exposed by this MCP server |
| Send an APRS message (max ~60 chars) |
| Last known position, aprs.fi API first, live stream fallback |
| Stations transmitting within a radius |
| Stream raw or parsed packets against an APRS-IS filter |
aprs_listen filter syntax
Example | Meaning |
| Station NOCALL |
| Radius filter around lat/lon, 50 km |
| Messages to/from NOCALL |
| Positions and objects only |
Related MCP server: A2A Client MCP Server
Requirements
Requires Python 3.11+ and uv.
Installation
git clone https://github.com/gflerm/aprs-mcp.git
cd aprs-mcp
uv sync
cp credentials.example credentialsOn Windows PowerShell, the included installer creates the virtual environment and credentials template:
.\install.ps1MCP client configuration
Codex
Register the local STDIO server globally:
codex mcp add aprs -- ".venv\Scripts\aprs-mcp.exe"On macOS or Linux, use .venv/bin/aprs-mcp instead. Restart Codex after
registration, then run aprs_cmd_list to verify the connection.
Other clients
opencode — add to ~/.config/opencode/opencode.json:
{
"mcp": {
"aprs": {
"type": "local",
"command": [".venv/bin/aprs-mcp"],
"enabled": true
}
}
}Claude Desktop — add to claude_desktop_config.json under mcpServers.
Any other MCP client — point it at the mcp stdio transport with command
.venv/bin/aprs-mcp (Windows: .venv\Scripts\aprs-mcp.exe).
Restart the agent after registering the server.
Credentials
The server reads network settings and station identity from a plain
key=value file named credentials in the project. Copy
credentials.example to credentials and fill in your own values.
The server looks for credentials in this order:
Next to the installed module (site-packages)
The project root (the checkout / install directory)
The current working directory
Existing environment variables always win; the file never overrides them.
Populate the credentials file as follows:
Key | Type | Meaning |
| required | Your base callsign, e.g. |
| required | APRS-IS passcode for the callsign. Use |
| optional | APRS-IS server, default |
| optional | Default |
| optional | aprs.fi API key for fast |
| optional | NTP server for local timezone, default |
Getting your passcode. The passcode is a one-way hash of your base
callsign — generate it once with the APRSPASS calculator shipped inside
aprslib:
python -c "from aprslib import passcode; print(passcode('ZL1XXXX'))"Then write the result into credentials:
APRS_CALLSIGN=ZL1XXXX
APRS_PASSCODE=12345
APRS_HOST=euro.aprs2.net
APRS_PORT=14580Optionally add your aprs.fi key (free, low-volume) so aprs_position
answers without waiting on the live stream.
credentials is your real file. credentials.example is the committed
template. Never commit credentials.
Development
Install the project in its managed virtual environment:
uv sync
uv run python -m aprs_mcp.serverThe MCP transport uses standard input/output. Client logs and diagnostics must go to standard error so they do not corrupt the protocol stream.
License
Released under the MIT License.
Available Tools
5 toolsaprs_cmd_listA
List the APRS tools exposed by this MCP server.
Inputs: no named parameters. Returns: result
aprs_listenA
Stream packets matching an APRS-IS filter string for a fixed duration.
Inputs: filter_text (required), raw, duration, max_packets. Returns: result
aprs_nearbyA
List APRS stations transmitting within a radius of a latitude/longitude.
Inputs: lat (required), lon (required), radius_km (required), timeout. Returns: result
aprs_positionA
Look up the last known position(s) of a callsign.
If APRSFI_API_KEY is configured, the aprs.fi API is queried first for the station's last known location (fast, reliable). Otherwise the APRS-IS stream is listened to with a station filter until a matching packet is received or the timeout expires.
Inputs: callsign (required), timeout. Returns: result
aprs_send_messageA
Send an APRS message to another callsign via APRS-IS.
Inputs: message (required), to_callsign (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose: sending messages, looking up positions, finding nearby stations, streaming raw packets, and listing commands. There is minimal overlap between these operations.
All tools share the 'aprs_' prefix, but the pattern is inconsistent: some use verb_noun (send_message), some are bare verbs (listen), and others are nouns or adjectives (position, nearby). The naming is readable but does not follow a single consistent convention.
With 5 tools, the server is well-scoped for its purpose. Each tool serves a distinct APRS-related function, and the count is neither overwhelming nor too sparse.
The toolset covers key APRS operations: sending messages, retrieving positions, discovering nearby stations, and listening to filtered packet streams. Missing advanced features like weather data or route history are minor gaps that do not impede core workflows.
Maintenance
Related MCP Connectors
Hosted MCP server for live public-data APIs and Skills for AI agents.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server exposing the Backtest360 engine API as tools for AI agents.
Real-time planetary signal engine and Model Context Protocol (MCP) server for autonomous AI agents.
Related MCP Servers
- AlicenseBqualityDmaintenanceAn MCP server that provides LLMs access to other LLMs456 npm83MIT
- AlicenseAqualityDmaintenanceAn MCP server that enables LLMs to interact with Agent-to-Agent (A2A) protocol compatible agents, allowing for sending messages, tracking tasks, and receiving streaming responses.528MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that publishes CLI tools on your machine for discoverability by LLMs4 npm1MIT
- AlicenseAqualityDmaintenanceAn MCP server that exposes WiGLE.net wardriving lookups as tools for LLMs, enabling searches and details for WiFi networks, Bluetooth devices, and cell towers.82MIT