mcpField
I
itu-zones-mcp

itu-zones-mcp

Local
github.com/qso-graphGames & Entertainment0Updated today

About itu-zones-mcp

itu-zones-mcp serves the IARU's 90 ITU zones for amateur-radio use, with prefixes and boundaries expressed in ADIF codes. It is intended for operators and tools that need source-cited zone lookups without network access or authentication.

Key features

  1. 01Look up zone prefixes and boundaries
  2. 02Map ADIF entities to zones
  3. 03Search zones by prefix or wording
  4. 04Check zone validity on a date
  5. 05Return source and edition details

Use cases

  1. 01Identify the ITU zone for a location
  2. 02Find areas covered by a zone
  3. 03Search zones using a prefix
  4. 04Check the cited source edition

MCP support

Exposes zone lookup, ADIF entity mapping, search, date-validity and source-information tools to MCP clients. The packaged data is served without network access or authentication.

Configuration

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

mcp.json · Universal config
{
"mcpServers": {
"qso-graph-itu-zones": {
"command": "uvx",
"args": [
"itu-zones-mcp"
]
}
}
}
Run commanduvx itu-zones-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
pypiitu-zones-mcp0.3.0

Tools

6

Saved tool list · updated 2d ago

This tool takes no parameters.

Details

From the project README

itu-zones-mcp

PyPI MCP Registry

Source: the IARU's HF Managers Handbook, chapter 9.8, "Definition of ITU-Zones when used by radio amateurs" (IARU Region 1, v8.2; the chapter's pages are dated November 2000). The zone border-lines for amateur use are kept there under IARU Region 1 recommendation REC/99/LH/C4.2; the list was drafted by G3HTA from the ITU's CIRAF zones and approved by all three IARU regions. The 90 ITU zones are the IARU's: this package serves facts from that chapter, each citing its page and zone, and links to the handbook rather than copying it. Our GPL-3.0 licence covers our code, not the IARU's data.

Checked against: AD1C's country files (Jim Reisert, AD1C), ADIF 3.1.7's subdivision zones, and ARRL's DXCC list. The tests fetch AD1C's and ARRL's files from their sites to validate the facts; neither is included here. where they differ, the owner's list wins (see docs/TRANSCRIPTION.md).

MCP server for ITU zones as the IARU publishes them for amateur use: the 90 zones of chapter 9.8, "Definition of ITU-Zones when used by radio amateurs", of the IARU Region 1 HF Managers Handbook (v8.2), used by the IARU HF Championship and ITU-zone awards. Each zone's prefixes are given in ADIF's own DXCC and subdivision codes, with the IARU's own wording where it splits an area by a line.

Part of the qso-graph project. No network, no authentication: the facts from the owner's list ship with the package, and every answer names its source.

Install

uvx itu-zones-mcp            # run it; nothing to install

Tools

ToolDescriptionKey Parameters
itu_zones_lookupOne zone: every prefix, subdivision and boundary the IARU lists, with the citationcode
itu_zones_codes_forWhich zones cover an ADIF DXCC entity, or one of its subdivisionsdxcc, subdivision
itu_zones_searchFind zones by prefix or wordingtext, limit
itu_zones_valid_onWhether a zone was valid on a date (ITU zones have no validity window)code, on_date
itu_zones_source_infoOwner, edition, terms, and the owner's file's URL and SHA-256—
get_version_infoService version + the owner's edition served (fleet identity attestation)—

Quick Start

No credentials needed — just install and configure your MCP client.

Configure your MCP client

itu-zones-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": {
    "itu-zones": {
      "command": "uvx",
      "args": ["itu-zones-mcp"]
    }
  }
}
Claude Code

Add to .claude/settings.json:

{
  "mcpServers": {
    "itu-zones": {
      "command": "uvx",
      "args": ["itu-zones-mcp"]
    }
  }
}
ChatGPT Desktop
{
  "mcpServers": {
    "itu-zones": {
      "command": "uvx",
      "args": ["itu-zones-mcp"]
    }
  }
}
Cursor

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

{
  "mcpServers": {
    "itu-zones": {
      "command": "uvx",
      "args": ["itu-zones-mcp"]
    }
  }
}
VS Code / GitHub Copilot

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

{
  "servers": {
    "itu-zones": {
      "command": "uvx",
      "args": ["itu-zones-mcp"]
    }
  }
}
Gemini CLI

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

{
  "mcpServers": {
    "itu-zones": {
      "command": "uvx",
      "args": ["itu-zones-mcp"]
    }
  }
}
Ask questions

"Which ITU zone is Arizona in?"

"What does ITU zone 75 cover?"

"Which ITU zones does Antarctica span?"

MCP Inspector

itu-zones-mcp --transport streamable-http --port 8017

Then open the MCP Inspector at http://localhost:8017.

Development

git clone https://github.com/qso-graph/itu-zones-mcp.git
cd itu-zones-mcp
uv sync --group dev
uv run pytest

scripts/fetch_published.py fetches the owner's document(s) into published/ (not committed) and checks their SHA-256s; uv run pytest --live runs the tests that need them. scripts/build.py regenerates derived/ and load.sql, a PostgreSQL load for QSO Graph's reference data (load QG ADIF's adif schema first).

License

itu-zones-mcp's own code is GPL-3.0-or-later. See LICENSE. The data it serves is the owner's, credited at the top of this page: our licence doesn't cover it, and we claim no rights in it. The owner's document itself is not included; data/SOURCE.json records its URL and SHA-256 so anyone can check the facts against it. Files we built from the facts (data/derived/) are ours and labelled as ours. How the owner's text was read is recorded in docs/TRANSCRIPTION.md. See NOTICE.

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.