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., "@jp-statistics-mcp 総人口の指標を検索して最新データを教えて"
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.
統計ダッシュボードの指標と、日本銀行の時系列統計を調べるMCPサーバーです。MCP、CLI、Pythonライブラリから同じ機能を使えます。
準備 · MCP登録 · CLI · Python · 移行手順
Python 3.12以上、uv、Gitが必要です。
git clone https://github.com/koizumikento/jp-statistics-mcp.git
cd jp-statistics-mcp
uv sync --lockedAPIキーは不要です。
Related MCP server: estat-mcp
設定例の /absolute/path/to/jp-statistics-mcp をクローン先の絶対パスに置き換えます。Windowsでは C:/projects/jp-statistics-mcp のように書けます。
codex mcp add jp-statistics-mcp -- uv --directory "/absolute/path/to/jp-statistics-mcp" run --locked jp-statistics-mcp
codex mcp list新しいセッションで /mcp を開いて接続状態を確認します。
Claude DesktopはOSに応じて次のファイルに設定します。
Windowsは %APPDATA%/Claude/claude_desktop_config.json
macOSは ~/Library/Application Support/Claude/claude_desktop_config.json
Cursorはプロジェクト内の .cursor/mcp.json を使います。mcpServers に次の項目を追加し、クライアントを再起動してください。
{
"mcpServers": {
"jp-statistics-mcp": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/jp-statistics-mcp",
"run",
"--locked",
"jp-statistics-mcp"
]
}
}
}uv が見つからない場合は、command に実行ファイルの絶対パスを指定してください。
データごとの入力条件、結果、出典と利用条件は、表のリンク先に記載しています。
ツール | データと操作の説明 |
| |
| |
| |
| |
| |
| |
| |
| |
| |
|
クローン先で実行します。取得結果はUTF-8のJSONとして標準出力に書き出します。
uv run jp-statistics-mcp dashboard search-indicators --query 総人口 --limit 3
uv run jp-statistics-mcp boj search-series --database fm08 --query ドル --limit 3引数の説明は、各サブコマンドに --help を付けて確認できます。
自分のPythonプロジェクトの依存関係に追加します。
uv add "git+https://github.com/koizumikento/jp-statistics-mcp.git@main"次のコードを example.py に保存し、uv run python example.py で実行します。
import asyncio
from jp_statistics_mcp import search_indicators
result = asyncio.run(search_indicators(query="総人口", limit=3))
print(result)ツールと同じ名前の非同期関数を利用できます。すでにイベントループがある場合は、直接 await してください。
コードはMITライセンスです。データは実行時に各提供元から取得します。取得データには、データ別の説明に記載した提供元の利用条件が適用されます。
uv sync --locked
uv run ruff check .
uv run ty check
uv run pytest
uv buildGet series data. Cycles: 1 month, 2 quarter, 3 calendar year, 4 fiscal year.
Inputs: indicator_code (required), cycle, limit, offset, +1 more. Returns: object
Fetch up to 250 codes from one DB and one frequency. Resume from NEXTPOSITION.
Inputs: database (required), end_period (required), series_codes (required), start_period (required), +1 more. Returns: object
Fetch observations for one BOJ series. Periods are YYYY or YYYYMM by frequency.
Inputs: database (required), end_period (required), series_code (required), start_period (required), +1 more. Returns: object
Fetch observations by comma-separated layer path (e.g. '1,2,*'). Resume from NEXTPOSITION.
Inputs: layer (required), database (required), frequency (required), end_period (required), +2 more. Returns: object
Find indicator codes by Japanese or English text in the indicator name.
Inputs: query (required), limit, offset. Returns: object
Find region codes by name, kana reading or code. Omit query to browse.
Inputs: limit, query, offset. Returns: object
Find series by Japanese name, English name or code within a BOJ database.
Inputs: query (required), database (required), limit, offset. Returns: object
Find social events by name or code, with their periods and statistical categories.
Inputs: limit, query, offset. Returns: object
Find statistical surveys by name or code, with agency, summary and reference link.
Inputs: limit, query, offset. Returns: object
Find statistical terms by name or code and read definitions and reference links.
Inputs: limit, query, offset. Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 10 tools
The six search_* tools are cleanly separated by entity (indicator, region, term, social event, survey, series), but the data-fetch tools overlap: get_series_data, get_multiple_series_data, get_series_data_by_layer and get_indicator_data all sound like 'get time series data' and only the descriptions reveal that two are BOJ-series based and two are e-Stat layer/indicator based. The shared word 'series' across both e-Stat and BOJ tools invites misselection.
All tools are snake_case with a verb_noun shape (search_*, get_*_data), so the pattern is predictable. Minor deviations: get_series_data_by_layer and get_multiple_series_data are longer qualified variants, and get_indicator_data lacks the 'series/indicator' symmetry with its siblings.
Ten tools is a well-scoped count for a server spanning two data sources (e-Stat catalog entities plus BOJ series). Each tool maps to a distinct entity or fetch mode, with no obviously redundant entries.
There is search coverage for indicators, regions, terms, events, surveys and BOJ series plus data retrieval, but gaps remain: no tool to enumerate available databases/layers (the layer path required by get_series_data_by_layer and the 'one DB' required by get_multiple_series_data must come from outside the toolset), and no metadata/definition lookup for a BOJ series beyond the name search. Pagination via NEXTPOSITION is handled for only two of the fetch tools.
Japanese law, corporation & statistics data as MCP, normalized to English with source attribution.
Authoritative JLPT-graded Japanese dataset (kanji, vocab, grammar, history) via MCP and REST.
政府統計 (e-Stat) の API を通じて、統計データやメタ情報を取得するためのサービスです。
Japan Law MCP — Japanese national laws & ordinances via the e-Gov Law API.
