Ionis Mcp

Name: Ionis Mcp
Author: qso-graph

@qso-graph

リポジトリ

Ionis Mcp について

MCP server for IONIS HF propagation analytics — 175M signatures from WSPR, RBN, Contest, DXpedition, and PSK Reporter.

#amateur-radio #propagation #hf #wspr #solar

基本情報

カテゴリ

データと分析

ライセンス

NOASSERTION

ランタイム

python

トランスポート

stdio

公開者

qso-graph

投稿者

Greg Beam

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "ionis": {
      "command": "ionis-mcp"
    }
  }
}

ツール

Show available datasets with row counts and file sizes

Flexible signature lookup — filter by source, band, grid, hour, month

Hour-by-hour propagation profile for a path on a specific band

Complete path analysis across all bands, hours, months, and sources

SFI effect on propagation — grouped by solar flux bracket

Maidenhead grid decode with solar elevation computation

Cross-dataset comparison (WSPR vs RBN vs Contest vs PSKR)

Classify paths by solar geometry — both-day, cross-terminator, both-dark

Historical solar indices for any date range

Band overview — hour distribution, top grid pairs, distance range

Live propagation forecast — SFI, Kp, solar wind, band outlook, POTA/SOTA tips

Service version + upstream dataset version (fleet identity attestation)

概要

What is Ionis Mcp?

A Model Context Protocol (MCP) server for HF radio propagation analytics, built on the IONIS dataset collection — 175M+ aggregated signatures derived from 14 billion WSPR, RBN, Contest, DXpedition, and PSK Reporter observations spanning 2005–2026. It bridges those datasets to AI assistants via MCP, allowing natural language queries about shortwave propagation. Designed for amateur radio operators, researchers, and propagation enthusiasts.

How to use Ionis Mcp?

Install with pip install ionis-mcp, then download datasets using ionis-download --bundle minimal (or recommended/full). Configure your MCP client (e.g., Claude Desktop) by adding a server entry with "command": "ionis-mcp"; restart the client for the 11 tools to appear. No environment variables are needed unless using a custom data directory (--data-dir or IONIS_DATA_DIR).

Key features of Ionis Mcp

11 specialized tools for propagation queries — no SQL required
175M+ aggregated signatures from 5 major telemetry networks
Cross-dataset comparisons (WSPR vs RBN vs Contest vs PSKR)
Solar indices and real-time DSCOVR solar wind data included
Read-only SQLite connections with parameterized queries
Graceful degradation when datasets are missing

Use cases of Ionis Mcp

Ask when 20m is open from Idaho to Europe
Analyze how solar flux affects 15m propagation
Compare WSPR and RBN observations on 20m between two grids
Get live propagation forecast with POTA/SOTA band tips
Classify paths by solar geometry (both-day, cross-terminator, both-dark)

FAQ from Ionis Mcp

What datasets does Ionis Mcp use?

The IONIS dataset collection: aggregated signatures from WSPR (93.6M), RBN (67.3M), CQ Contests (5.7M), DXpeditions (260K), and PSK Reporter (8.4M), plus solar indices and DSCOVR solar wind data. All signature tables share a common 13-column schema.

How do I install and configure Ionis Mcp?

Install with pip install ionis-mcp, then download data with ionis-download --bundle recommended. Add the server config to your MCP client (e.g., Claude Desktop) specifying "command": "ionis-mcp". No environment variables are needed unless using a custom data directory.

Does Ionis Mcp require an internet connection?

The datasets are downloaded locally via ionis-download. Once downloaded, the server queries local SQLite files directly — no ongoing internet connection is needed.

What transports and authentication does Ionis Mcp support?

It supports stdio transport (for Claude Desktop/Code) and streamable-http transport (for MCP Inspector). No authentication is described; the server runs locally on your machine.

What are the size requirements for the datasets?

Minimal bundle ~430 MB (contest, solar, grids), recommended ~1.1 GB (adds PSKR and DSCOVR), full ~15 GB (all 9 datasets). The server works with whatever datasets are present — missing datasets degrade gracefully.

「データと分析」の他のコンテンツ

Healthcare MCP Server

Cicatriiz

A Model Context Protocol (MCP) server providing AI assistants with access to healthcare data and medical information tools, including FDA drug info, PubMed, medRxiv, NCBI Bookshelf, clinical trials, ICD-10, DICOM metadata, and a medical calculator.

117