これは、Alpha Vantage APIから株式市場データを提供するモデルコンテキストプロトコル（MCP）サーバーです。ClaudeをはじめとするMCPクライアントは、このサーバーを通じてリアルタイムおよび過去の株式データにアクセスできます。
カスタマイズ可能な間隔で日中株価データを取得する
毎日の株価データを取得する
価格変動に基づいて株価アラートを生成する
株価データをリソースとしてアクセス
Related MCP server: Alpha Vantage MCP Server
Node.js 16以上
Alpha Vantage API キー ( Alpha Vantageで無料で取得できます)
このリポジトリをクローンする
依存関係をインストールします:
npm installルート ディレクトリに.envファイルを作成し、Alpha Vantage API キーを追加します。
ALPHA_VANTAGE_API_KEY=your_api_key_hereTypeScript コードをビルドします。
npm run buildサーバーを実行します。
npm start自動リロードを使用した開発の場合:
npm run devAPI クライアントをテストします。
npm testこの MCP サーバーを Claude for Desktop で使用するには:
デスクトップ版Claudeを開く
設定 > 開発者 > 設定の編集に移動します
claude_desktop_config.jsonに以下を追加します。
{
"mcpServers": {
"alpha-vantage": {
"command": "node",
"args": ["/absolute/path/to/dist/index.js"],
"env": {
"ALPHA_VANTAGE_API_KEY": "YOUR_API_KEY"
}
}
}
}/absolute/path/to/dist/index.js 、構築された index.js ファイルへの絶対パスに置き換えます。
デスクトップ版のClaudeを再起動
特定のシンボルの日中株価データを取得します。
パラメータ:
symbol （必須）：株式シンボル（例：IBM、AAPL）
interval （オプション）：データポイント間の時間間隔（1分、5分、15分、30分、60分）。デフォルト：5分
outputsize （オプション）：返されるデータの量（コンパクト：最新の100データポイント、フル：最大20年間のデータ）。デフォルト：コンパクト
特定のシンボルの毎日の株価データを取得します。
パラメータ:
symbol （必須）：株式シンボル（例：IBM、AAPL）
outputsize （オプション）：返されるデータの量（コンパクト：最新の100データポイント、フル：最大20年間のデータ）。デフォルト：コンパクト
株価データを分析して、価格変動に基づいてアラートを生成します。
パラメータ:
symbol （必須）：株式シンボル（例：IBM、AAPL）
threshold （オプション）：価格変動アラートのしきい値（パーセント）。デフォルト：5
リソースとして株価データに直接アクセスします。
URI テンプレート: stock://{symbol}/{interval}
パラメータ:
symbol : 株式シンボル（例: IBM、AAPL）
interval : 時間間隔（毎日、1分、5分、15分、30分、60分）。デフォルト: daily
Claude での使用例:
「この株価データを分析できますか: stock://AAPL/daily」
「このデータについてどう思いますか: stock://MSFT/5min」
マサチューセッツ工科大学
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Stock symbol (e.g., IBM, AAPL) | |
| outputsize | No | Amount of data to return (compact: latest 100 data points, full: up to 20 years of data) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Stock symbol (e.g., IBM, AAPL) | |
| threshold | No | Percentage threshold for price movement alerts (default: 5) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Stock symbol (e.g., IBM, AAPL) | |
| interval | No | Time interval between data points (default: 5min) | |
| outputsize | No | Amount of data to return (compact: latest 100 data points, full: up to 20 years of data) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0get-daily-stock-dataget-stock-alertsget-stock-dataScored across 3 tools
The tools are highly ambiguous and overlapping. 'get-daily-stock-data' and 'get-stock-data' appear to serve nearly identical purposes, with no description to clarify differences. 'get-stock-alerts' might be distinct but lacks context, making it unclear how it differs from the data retrieval tools. This setup will likely cause frequent agent misselection.
The naming follows a consistent pattern with kebab-case and a 'get-' verb prefix across all tools, which is predictable and readable. However, the lack of descriptions prevents full evaluation of semantic consistency, but structurally, the naming is uniform.
With only 3 tools, this server feels under-scoped for a stock analysis domain, which typically requires more operations like historical data, indicators, or portfolio management. The count is too low to provide comprehensive coverage, limiting agent capabilities.
The tool set is severely incomplete for stock analysis. It lacks essential operations such as intraday data, technical indicators, company fundamentals, or search functions. With only basic data retrieval and alerts, agents will face dead ends and cannot perform meaningful analysis.
Alpha Vantage MCP — Stock market data, fundamentals, and earnings
Financial data MCP server for Claude, ChatGPT, Cursor and Codex. Real-time stock quotes, financial statements, options flow, SEC filings, insider trades, 13F holdings, macro data and market news from gloom.sh, the open-source Bloomberg Terminal alternative.
Twelve Data MCP: real-time & historical market data (stocks, crypto, forex, etc).
Stock market data for AI agents: real-time quotes, financials, options, SEC filings and news.
