io.github.MicaelJarniac/repeaterbook
Provides tools to manage and query a local SQLite database of repeater data, including populating, searching, and clearing the local store.
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., "@io.github.MicaelJarniac/repeaterbookfind 2-meter repeaters near Portland, OR"
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.
| |
| |
| |
| |
|
RepeaterBook Python Client
Unofficial project. RepeaterBook Python Client is an independent, community-maintained library and MCP server, and is not affiliated with, endorsed by, or officially supported by RepeaterBook.com. "RepeaterBook" is a trademark of its respective owner. For the official website and API, visit https://repeaterbook.com/.
Welcome to the RepeaterBook Python Client documentation!
RepeaterBook Python Client is an unofficial, third-party Python library and Model Context Protocol (MCP) server that provides a powerful and convenient interface to the RepeaterBook.com API — the world's largest database of amateur radio repeaters. Use it as a library to programmatically download, query, and analyze repeater data, or run the bundled MCP server to give AI agents and LLM tools the same repeater lookup capabilities.
Features
Easy API Access: Download repeater data from RepeaterBook.com with a simple async interface
Unofficial MCP Server: Ship repeater sync, geographic search, lookup, and a local-data wipe to any MCP client as four typed tools — see the MCP Server guide
Local Database: Store repeater information in a local SQLite database for fast queries
Geographic Queries: Find repeaters near a location using distance-based filtering
Band Filtering: Query repeaters by frequency band (2m, 70cm, etc.)
Digital Mode Support: Filter by DMR, P25, NXDN, and other digital modes
Smart Caching: Automatic caching of API responses to reduce load and improve performance
Type Safe: Fully typed with mypy for excellent IDE support
Async/Await: Non-blocking I/O for efficient API operations
Related MCP server: Sentinel Core Agent
Quick Example
You need a RepeaterBook API token. No application registration required — this library is already registered as RepeaterBook Python Client (App #114). Log in to RepeaterBook, open API Applications, find App #114, and generate a token. Then expose it as the
REPEATERBOOKenvironment variable (for exampleexport REPEATERBOOK="rbuapp_..."). Keep the library's defaultUser-Agent— see the Authentication guide.
import asyncio
import os
from repeaterbook import RepeaterBook, Repeater
from repeaterbook.services import RepeaterBookAPI
from repeaterbook.models import ExportQuery, Status
from repeaterbook.utils import LatLon, Radius
from repeaterbook.queries import filter_radius, square, band, Bands
import pycountry
async def find_nearby_repeaters():
# Download repeater data
api = RepeaterBookAPI(app_token=os.environ["REPEATERBOOK"])
brazil = pycountry.countries.get(name="Brazil")
repeaters = await api.download(query=ExportQuery(countries={brazil}))
# Store in local database
rb = RepeaterBook()
rb.populate(repeaters)
# Find DMR repeaters within 50km of São Paulo
sao_paulo = LatLon(lat=-23.5505, lon=-46.6333)
radius = Radius(origin=sao_paulo, distance=50)
nearby = rb.query(
square(radius),
Repeater.dmr_capable == True,
Repeater.operational_status == Status.ON_AIR,
band(Bands.CM_70) # 70cm band
)
filtered = filter_radius(nearby, radius)
# Display results (filter_radius returns repeaters sorted by distance)
from haversine import haversine
for rep in filtered[:5]:
distance = haversine(radius.origin, (rep.latitude, rep.longitude), unit=radius.unit)
print(f"{distance:.1f}km - {rep.frequency:.4f} MHz - {rep.callsign}")
asyncio.run(find_nearby_repeaters())Quick Example (MCP)
Prefer to drive RepeaterBook from an AI agent? The unofficial MCP server ships as
the repeaterbook-mcp console script behind the mcp extra. Point your MCP
client at uvx and nothing needs installing up front:
{
"mcpServers": {
"repeaterbook": {
"command": "uvx",
"args": ["--from", "repeaterbook[mcp]", "repeaterbook-mcp"],
"env": {
"REPEATERBOOK_WORKING_DIR": "~/.repeaterbook",
"REPEATERBOOK_APP_TOKEN": "rbuapp_..."
}
}
}
}REPEATERBOOK_APP_TOKEN is the same App #114 token described above; the
server won't start without it.
That exposes four tools — sync_repeaters, search_repeaters, and
get_repeater, which return a stable, source-agnostic repeater spec, plus
clear_local_data to wipe the local store and response cache. See the
MCP Server guide for the full tool reference, filter vocabulary,
and configuration options.
Documentation
Getting Started - Tutorial for beginners
Usage Guide - Comprehensive usage examples
MCP Server - Run the unofficial MCP server for AI agents
Examples - Real-world use cases
Architecture - Understanding the internals
API Reference - Complete API documentation
FAQ - Common questions and troubleshooting
Read RepeaterBook.com's official API documentation for more information about the upstream API.
Use Cases
AI Agents & Assistants: Let an LLM look up repeaters conversationally over MCP
Trip Planning: Find repeaters along travel routes
Emergency Communications: Identify emergency-capable repeaters
Radio Programming: Generate codeplugs for DMR and other digital radios
Coverage Analysis: Create coverage maps and statistics
Network Analysis: Analyze repeater networks and infrastructure
Mobile Apps: Build repeater directory applications
Research: Analyze amateur radio repeater trends and distributions
Related Projects
MicaelJarniac/opengd77 - OpenGD77 radio programming
MicaelJarniac/ogdrb - OpenGD77 RepeaterBook integration
See Also
afourney/hamkit - Ham radio toolkit
desertblade/OpenGD77-Repeaterbook - OpenGD77 integration
TomHW/OpenGD77 - OpenGD77 firmware
Installation
PyPI
repeaterbook is available on PyPI:
# With uv (recommended)
uv add repeaterbook
# With pip
pip install repeaterbook
# With Poetry
poetry add repeaterbookMCP server
The MCP server lives behind the mcp extra. Most MCP clients should invoke it
via uvx, with no install step at all:
# Run on demand, no install (what MCP clients should use)
uvx --from "repeaterbook[mcp]" repeaterbook-mcp
# Or install it persistently
uv tool install "repeaterbook[mcp]"
# Or add it as a project dependency
uv add "repeaterbook[mcp]"
pip install "repeaterbook[mcp]"GitHub
You can also install the latest version of the code directly from GitHub:
# With uv
uv add git+https://github.com/MicaelJarniac/repeaterbook
# With pip
pip install git+https://github.com/MicaelJarniac/repeaterbook
# With Poetry
poetry add git+https://github.com/MicaelJarniac/repeaterbookRequirements
Python 3.11 or higher
Dependencies are automatically installed:
aiohttp - Async HTTP client
anyio - Async compatibility layer
attrs - Immutable config classes
haversine - Distance calculations
loguru - Structured logging
pycountry - Country/region codes
pydantic - Data validation
sqlmodel - SQL ORM with type safety
tqdm - Progress bars
yarl - URL handling
The optional
mcpextra additionally installsfastmcp,pydantic-settings, andpydantic[email](for theEmailStrcontact setting)
Contributing
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
Please make sure to update tests as appropriate.
More details can be found in CONTRIBUTING.
Contributors ✨
License
This project was created with the MicaelJarniac/crustypy template.
This server cannot be deployed
Maintenance
Related MCP Connectors
Real-time Amazon, WIPO & PACER data for AI agents — 19 tools via the MCP protocol.
A registry of AI agent tools — MCP servers, APIs, CLIs, SDKs — kept current by automated ingestion.
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
- geoOAuthco.thinair
Geocoding, routing, isochrones, traffic, weather, and place search for AI agents. 19 MCP tools.
Related MCP Servers
- AlicenseAqualityDmaintenanceMCP server for HamQTH.com — callsign lookup, DX cluster spots, Reverse Beacon Network, DXCC resolution, and more through any MCP-compatible AI assistant.825 PyPIGPL 3.0
- FlicenseNot gradedqualityDmaintenanceEnables file system operations, web scraping, and AI-powered search through MCP tools for use by LLM agents.1-
- AlicenseAqualityCmaintenanceEnables querying WSPR beacon data including live spots, band activity, top beacons, propagation paths, and SNR trends through any MCP-compatible AI assistant.922 PyPIGPL 3.0
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to access a unified catalog of tools from various APIs (OpenAPI, GraphQL, MCP, Google Discovery) through the MCP protocol.173 npmMIT