- ✓Actively maintained (<30d)
- ✓Documented (README)
- !No standard license detected
- !No description
git clone https://github.com/atushi1841/japan-stock-mcpTools overview
# Japan Stock Market Data MCP(東証株価・市場データ・日本株 screener)
TSE 株式・市場データ MCP サーバー — 東京証券取引所の株価・市場データを AI エージェントに提供。
公式 API(J-Quants / JPX)を使用するため **TOS リスクなし・無料枠あり**。
## Tools(MCP ツール一覧)
| ツール名 | 機能 |
|---|---|
| `get_quote(code, days)` | 指定銘柄の最新日足 OHLCV(高値・安値・出来高含む) |
| `screener(market, sector, min_market_cap, ...)` | 市場・業種・時価総額・価格・値幅で株をスクリーニング |
| `get_valuation(code)` | 時価総額・PER・PBR・配当利回り |
| `get_financial_summary(code, period)` | 売上高・営業利益・純利益(四半期累計) |
| `get_calendar(year, month)` | 取引カレンダー(休日リスト) |
| `sector_list()` | 33業種 / 17業種 分類コードマッピング |
## 動作要件
- Python >= 3.10、fastmcp / mcp
- 無料枠: J-Quants 無料プラン(12週間データラグ)
- 認証: `JQUANTS_API_KEY` 環境変数(https://jpx-jquants.com で無料登録)
- 完全ローカル実行(stdio / HTTP 両対応)
## Quickstart
```bash
# 1. クローン
git clone https://github.com/atushi1841/japan-stock-mcp.git
cd japan-stock-mcp
# 2. 依存
pip install fastmcp
# 3. stdio mode で起動(Claude Desktop 等から接続)
export JQUANTS_API_KEY="your-free-key"
python server.py
# 4. HTTP mode で起動
python server.py --http --port 8000
```
### 動作確認
```bash
python server.py --http --port 8000 &
sleep 2
curl -s -X POST http://localhost:8000/mcp/tools/list \
-H "Content-Type: application/json" \
-d '{}' | jq '.tools[].name'
```
## MCP 公開レジストリ登録状況
| レジストリ | 状態 | 備考 |
|---|---|---|
| MCP 公式レジストリ | ✅ 登録済み | `io.github.atushi1841/japan-stock-mcp` |
| Smithery | 📝 未登録 | MCPB バンドル作成済(v0.1.0)— 公開はユーザー手動操作待ち |
| mcp.so | 📝 未登録 | YAML テンプレは Kensho 側に `mcp_so_configs/` 予定 |
## 関連プロジェクト
- Kensho: https://github.com/atushi1841/kensho
- 既存 Japan MCP 系列: japan-ec-mcp, japan-price-alert-mcp, japan-intel-mcp, japan-market-mcp, japan-jepx-mcp, jartic-japan-traffic-mcp 等
## License
MIT License. See [Kensho](https://github.com/atushi1841/kensho) project for the full stack.What people ask about japan-stock-mcp
What is atushi1841/japan-stock-mcp?
+
atushi1841/japan-stock-mcp is tools for the Claude AI ecosystem with 0 GitHub stars.
How do I install japan-stock-mcp?
+
You can install japan-stock-mcp by cloning the repository (https://github.com/atushi1841/japan-stock-mcp) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is atushi1841/japan-stock-mcp safe to use?
+
Our security agent has analyzed atushi1841/japan-stock-mcp and assigned a Trust Score of 52/100 (tier: OK). See the full breakdown of passed checks and flags on this page.
Who maintains atushi1841/japan-stock-mcp?
+
atushi1841/japan-stock-mcp is maintained by atushi1841. The last recorded GitHub activity is dated 2026-10-16, with 0 open issues.
Are there alternatives to japan-stock-mcp?
+
Yes. On ClaudeWave you can browse similar tools at /categories/tools, sorted by popularity or recent activity.
Deploy japan-stock-mcp to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/atushi1841-japan-stock-mcp)<a href="https://claudewave.com/repo/atushi1841-japan-stock-mcp"><img src="https://claudewave.com/api/badge/atushi1841-japan-stock-mcp" alt="Featured on ClaudeWave: atushi1841/japan-stock-mcp" width="320" height="64" /></a>More Tools
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
Use Claude Code, Codex, VSCode, Pi, and OpenCode (and 6 other harnesses) for free (1.3B+ free tokens) from your terminal, app, IDE, or phone, and now from the browser with native browser sessions (multi-harness + multi-model) like OpenClaw (voice supported + ToS friendly)
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build, Muse Code, Devin as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini Series, GPT Series, Grok Series, Claude model through API