Qrz Mcp

qrz-mcp

[PyPI] [MCP Registry]

MCP server for QRZ.com — callsign lookups, DXCC entity resolution, and logbook queries through any MCP-compatible AI assistant.

Part of the qso-graph project. Uses qso-graph-auth for credential management.

Install

uvx qrz-mcp            # run it; nothing to install

Tools

Quick Start

1. Set up credentials

qrz-mcp uses qso-graph-auth personas for credential management. QRZ has two separate auth mechanisms, exposed as two providers — set up whichever you need:

# Install qso-graph-auth if you haven'tuv tool install qso-graph-auth
# Create a persona (--start is required)qso-graph-auth persona add --name ki7mt --callsign KI7MT --start 2018-01-01
# XML API (qrz_lookup, qrz_dxcc)qso-graph-auth provider enable ki7mt qrzqso-graph-auth creds set ki7mt qrz              # asks for your username, then your password (hidden)
# Logbook API (qrz_logbook_status, qrz_logbook_fetch, qrz_download)qso-graph-auth provider enable ki7mt qrz_logbookqso-graph-auth creds set ki7mt qrz_logbook      # asks for your username, then your API key
# Verifyqso-graph-auth creds doctor

Pass the persona name (ki7mt above) as the persona argument on every tool call.

Omit --password / --api-key to be prompted instead — passing secrets as CLI arguments leaves them in your shell history.

XML API (callsign lookup, DXCC) requires a QRZ XML Subscription ($35.95/yr). Free tier returns name and address only.

Logbook API requires an API key from QRZ Settings > API.

2. Configure your MCP client

qrz-mcp works with any MCP-compatible client. Add the server config and restart — tools appear automatically.

Claude Desktop

Add to claude_desktop_config.json (~/Library/Application Support/Claude/ on macOS, %APPDATA%\Claude\ on Windows):

{  "mcpServers": {    "qrz": {      "command": "uvx",      "args": ["qrz-mcp"]    }  }}

Claude Code

Add to .claude/settings.json:

{  "mcpServers": {    "qrz": {      "command": "uvx",      "args": ["qrz-mcp"]    }  }}

ChatGPT Desktop

ChatGPT supports MCP via the OpenAI Agents SDK. Add under Settings > Apps & Connectors, or configure in your agent definition:

{  "mcpServers": {    "qrz": {      "command": "uvx",      "args": ["qrz-mcp"]    }  }}

Cursor

Add to .cursor/mcp.json (project-level) or ~/.cursor/mcp.json (global):

{  "mcpServers": {    "qrz": {      "command": "uvx",      "args": ["qrz-mcp"]    }  }}

VS Code / GitHub Copilot

Add to .vscode/mcp.json in your workspace:

{  "servers": {    "qrz": {      "command": "uvx",      "args": ["qrz-mcp"]    }  }}

Gemini CLI

Add to ~/.gemini/settings.json (global) or .gemini/settings.json (project):

{  "mcpServers": {    "qrz": {      "command": "uvx",      "args": ["qrz-mcp"]    }  }}

3. Ask questions

"Look up W1AW on QRZ — what's their grid and license class?"

"What DXCC entity is VP8PJ?"

"How many QSOs do I have in my QRZ logbook?"

"Show me all 20m FT8 QSOs from my QRZ logbook this year"

Rate Limiting

QRZ enforces undocumented rate limits that can trigger 24-hour IP bans. qrz-mcp protects you:

• 500ms minimum delay between all API calls
• Token bucket: 35 requests/minute
• 60s freeze on authentication failures
• 3600s freeze on connection refused (IP ban detection)
• In-memory response cache (5 min for callsigns, 1 hour for DXCC)

Testing Without Credentials

Set the mock environment variable to test all 6 tools without QRZ credentials:

QRZ_MCP_MOCK=1 qrz-mcp

MCP Inspector

qrz-mcp --transport streamable-http --port 8002

Then open the MCP Inspector at http://localhost:8002.

Development

git clone https://github.com/qso-graph/qrz-mcp.gitcd qrz-mcpuv sync --group devuv run pytest

QRZ Subscription Tiers

License

GPL-3.0-or-later