About japan-intel-mcp
japan-intel-mcp is a read-only MCP server for agents and developers seeking Japanese public data on earthquakes, weather, typhoons, corporate filings, and postal codes. Responses include sources and identify data that could not be retrieved.
Key features
- 01Query earthquakes and weather alerts
- 02Get weather summaries and seven-day forecasts
- 03Track typhoon information
- 04Query EDINET corporate filings
- 05Resolve postal codes to addresses
- 06Return sources and data gaps
Use cases
- 01Retrieve Japanese earthquake and alert information
- 02Check forecasts for a specific area
- 03Find statutory corporate disclosures
- 04Look up addresses by postal code
MCP support
As an MCP server, it offers eight read-only tools for MCP clients to query Japanese public data, with sources and data gaps included in responses.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEjapan-intel-mcp
MCP server for Japanese public data — earthquakes, weather warnings, typhoons, weekly forecasts, corporate filings (EDINET), and postal-code lookup. Free, keyless, no API key required.
An MCP server that gives AI agents cross-source access to live Japanese public data with citations. Every response carries sources and data_gaps, so agents can tell what was retrieved and what was not.
Built for AI agents, LLM toolchains, and developers who need current Japan information without scraping or paying for a data vendor.
Why this exists
Most "global intelligence" MCP servers are built on Western data sources. Japanese public data is free and authoritative (Japan Meteorological Agency, EDINET, Japan Post) but scattered across HTML pages and undocumented endpoints. This server normalizes them behind 8 read-only tools.
- Free — no API key, no signup, no rate-limit tier
- Cited — every response includes
sources - Honest — failures are reported in
data_gaps, never silently dropped
Tools
| Tool | Description | Source |
|---|---|---|
japan_earthquakes(min_magnitude, min_intensity, limit) | Recent earthquakes: epicenter, magnitude, max intensity, depth | JMA (気象庁) |
japan_weather_warnings(area) | Active weather warnings/advisories, filterable by prefecture | JMA |
japan_weather_overview(prefecture) | Narrative weather summary (10 major prefectures) | JMA |
japan_weekly_forecast(prefecture) | 7-day forecast: high/low temps, precipitation probability, reliability | JMA |
japan_typhoons() | Active typhoon tracking | JMA |
japan_edinet_filings(date) | Statutory corporate disclosures (annual reports, timely disclosure) | EDINET |
japan_postal_lookup(zipcode) | Postal code → address (kanji and kana) | zipcloud |
japan_watch_summary(min_magnitude) | One-call cross-source summary of the above | JMA |
Response format
{
"retrieved_at": "2026-10-12T01:30:00+00:00",
"sources": ["https://www.jma.go.jp/bosai/quake/data/list.json"],
"data_gaps": [],
"data": []
}
Install
pip install -e .
Usage
japan-intel-mcp # stdio mode (Claude Code / Cursor / Hermes / any MCP client)
python -m japan_intel_mcp.server
Claude Code
{
"mcpServers": {
"japan-intel-mcp": {
"command": "japan-intel-mcp"
}
}
}
Hermes
mcp:
servers:
japan-intel:
command: japan-intel-mcp
Examples
japan_earthquakes(min_magnitude=4.0, limit=5)
japan_weather_warnings(area="Tokyo")
japan_weekly_forecast(prefecture="Tokyo")
japan_postal_lookup(zipcode="1000001")
japan_watch_summary(min_magnitude=3.0)
Where to get it
| Channel | Command / URL |
|---|---|
| MCP bundle | v0.2.1 release (.mcpb) |
| Official MCP registry | io.github.atushi1841/japan-intel-mcp |
| Apify (Standby MCP) | fruitful_quintessence/japan-intel-mcp (in preparation) |
| PyPI | pip install japan-intel-mcp (publication in progress) |
Design contract
- Always cite — every response includes a
sourceslist - Never hide gaps — unavailable sources appear in
data_gapsinstead of being silently omitted - Free only — no paid API keys anywhere
License
MIT
日本語
日本の公開情報を横断する読み取り専用の MCP サーバー。すべてのデータ源が無料・APIキー不要です。AIエージェントが「今の日本で何が起きているか」を、出典付きで取得できます。
- 出典を必ず返す: 各応答に
sourcesリストが入ります - 取れなかったものを隠さない: 取得に失敗したデータ源は
data_gapsに明示します - 無料のみ: 有料APIキーは一切不要です
ツール一覧は上部の表を参照してください(8ツール)。
MCP 公式レジストリ登録済み
本サーバーはMCP公式レジストリに登録済みです。
- Registry: MCP Registry
# レジストリでの確認
curl -s "https://registry.modelcontextprotocol.io/v0.1/servers?search=atushi1841" | grep -o "\"io.github.atushi1841/japan-intel-mcp\""
Data Source: Apify Store & Smithery Registry
This MCP server is available on:
- Apify Store: japan-intel-mcp — Japan public data (earthquakes, weather, EDINET, postal) MCP server
- Smithery Registry: Install via Smithery — MCP server for AI agents
Install via Smithery:
npx @smithery/cli install atushi1841/japan-intel-mcp --client claude
Data & Store
- Apify Store: https://apify.com/fruitful_quintessence
- Gumroad datasets: https://atushi5.gumroad.com/l/kutuxe
Comments
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.