mcpField
Q
Qrz Mcp

Qrz Mcp

Local
github.com/qso-graphGames & Entertainment3Updated today

About Qrz Mcp

Qrz Mcp exposes QRZ callsign, DXCC, and logbook operations to MCP-compatible clients. It separates credentials for QRZ's XML and Logbook APIs and includes request throttling and caching.

Key features

  1. 01Callsign and DXCC lookups
  2. 02Logbook status and filtered queries
  3. 03Full logbook download as ADIF
  4. 04Request throttling and response cache
  5. 05Credential personas for two APIs

Use cases

  1. 01Checking a callsign's grid and license class
  2. 02Resolving a callsign to a DXCC entity
  3. 03Reviewing or filtering QRZ logbook QSOs
  4. 04Exporting a QRZ logbook as ADIF

MCP support

The MCP server exposes QRZ lookup, DXCC, and logbook tools to MCP-compatible clients. It can run through stdio or streamable HTTP transport.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"qrz": {
"command": "uvx",
"args": [
"qrz-mcp"
]
}
}
}
Run commanduvx qrz-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiqrz-mcp0.6.0

Tools

6

Saved tool list · updated 2w ago

This tool takes no parameters.

Details

From the project README

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

ToolAPIAuthDescription
qrz_lookupXMLSession keyCallsign lookup (name, grid, DXCC, license class, QSL info, image)
qrz_dxccXMLSession keyDXCC entity resolution from callsign or entity code
qrz_logbook_statusLogbookAPI keyLogbook stats (QSO count, DXCC total, date range)
qrz_logbook_fetchLogbookAPI keyQuery QSOs with filters and transparent pagination
qrz_downloadLogbookAPI keyDownload full logbook as ADIF
get_version_info—NoneService version + upstream QRZ API version (fleet identity attestation)

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:

ProviderToolsCredentials
qrzqrz_lookup, qrz_dxccusername + password
qrz_logbookqrz_logbook_status, qrz_logbook_fetch, qrz_downloadusername + API key
# Install qso-graph-auth if you haven't
uv tool install qso-graph-auth

# Create a persona (--start is required)
qso-auth persona add --name ki7mt --callsign KI7MT --start 2018-01-01

# XML API (qrz_lookup, qrz_dxcc)
qso-auth provider enable ki7mt qrz
qso-auth creds set ki7mt qrz              # asks for your username, then your password (hidden)

# Logbook API (qrz_logbook_status, qrz_logbook_fetch, qrz_download)
qso-auth provider enable ki7mt qrz_logbook
qso-auth creds set ki7mt qrz_logbook      # asks for your username, then your API key

# Verify
qso-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.git
cd qrz-mcp
uv sync --group dev
uv run pytest

QRZ Subscription Tiers

FeatureFreeXML Data ($35.95/yr)
Callsign lookups/day100Unlimited
Fields returnedName + address onlyAll (grid, lat/lon, DXCC, class, QSL, image)
Logbook APINoYes
DXCC lookupNoYes

License

GPL-3.0-or-later

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.