広告掲載
MCP.so
ログイン
M

Market Data MCP Server

@cstamigo-droid

リポジトリ

基本情報

カテゴリ

データと分析

トランスポート

stdio

作者

cstamigo-droid

投稿者

cstamigo-droid

Market Data MCP Server について

概要はまだありません

Market Data MCP Server の設定

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": {
    "market-data-mcp": {
      "command": "python",
      "args": [
        "-m",
        "market_data_mcp"
      ],
      "cwd": "C:/path/to/market-data-mcp"
    }
  }
}

Market Data MCP Server のツール

6

Real-time price, % change, high/low/open/prev-close

Top 5 headlines — company-specific or general market

Earnings calendar for the next N days (with EPS/revenue estimates)

Watchlist scanner: rank up to 25 tickers by absolute % change

Composite: momentum score + news catalyst + earnings proximity

Read open positions from Alpaca paper account

概要

What is Market Data Mcp?

Market Data Mcp is a Model Context Protocol server that provides real-time market data—quotes, news, earnings calendars, and a watchlist scanner—to AI agents. It integrates with Finnhub as its primary data source and optionally Alpaca for broker positions. Designed for any MCP client (e.g., Claude Desktop, Claude Code), it returns clean, uniform results that fail gracefully rather than fabricating values.

How to use Market Data Mcp?

Clone the repository, create a Python virtual environment, install dependencies, and configure a .env file with FINNHUB_API_KEY. Run the server via python -m market_data_mcp. Add a mcpServers entry to your Claude Desktop configuration file. Tools are invoked by name (e.g., market_quote, market_scan) and return Markdown by default or JSON with response_format="json".

Key features of Market Data Mcp

  • Real-time quotes, news, earnings calendar, and watchlist scanner.
  • Composite analysis tool with directional score and confidence.
  • Uniform Result contract across all tools (source, ok, summary, data, score, confidence, error).
  • Graceful degradation: missing or premium-gated data returns Result.failed, never a fabricated value.
  • Per-source TTL cache to respect API rate limits.
  • Optional Alpaca paper account integration for reading open positions.

Use cases of Market Data Mcp

  • Ask an AI agent for the current price and daily change of a stock.
  • Get the top 5 market headlines or company-specific news.
  • Retrieve upcoming earnings calendar events with EPS and revenue estimates.
  • Scan a watchlist of up to 25 tickers and rank them by absolute percentage change.
  • Perform a composite analysis of a ticker including momentum, news catalyst, and earnings proximity.
  • Read open positions from an Alpaca paper trading account.

よくある質問

1

What data sources does Market Data Mcp use?

The primary source is Finnhub. The `broker_positions` tool optionally uses Alpaca’s Paper Trading API if API keys are provided.

2

Does Market Data Mcp require an API key?

Yes, you need a free Finnhub API key, obtainable at https://finnhub.io/register. The Alpaca keys are optional.

3

Are the tools free to use?

Most tools operate on Finnhub’s free tier. The earnings calendar tool was verified live on 2026-06-14 and accessible on the free tier. The `broker_positions` tool requires Alpaca keys but is free for paper trading.

4

What transport does Market Data Mcp use?

It uses the standard MCP transport over stdio, configured via Claude Desktop’s `mcpServers` JSON with a `command` and `args` pointing to the Python module.

5

What happens when data is unavailable?

The server returns a `Result.failed` object with an error message. It never fabricates a value—missing or premium-gated sources produce “no data.”

コメント

「データと分析」の他のコンテンツ

Draxlr

Vivek

Draxlr is a remote MCP server that connects AI assistants to your SQL databases. Explore schemas, run read-only queries, and work with your saved queries and dashboards over MCP. Hosted at https://api.draxlr.com with OAu

SocialAPIs — Facebook & Instagram Data

SocialAPIsHub

Facebook & Instagram data for AI agents — pages, posts, groups, Ads Library, Marketplace, profiles and reels. 47 read-only tools with structured output.

1

Jitsu

Jitsu

Jitsu is an open-source Customer Data Platform — an MIT-licensed alternative to Segment. This MCP server gives your AI assistant direct control over a Jitsu workspace, so you can run and debug data pipelines in conversat

CompanyData

CompanyData

Company search and enrichment for AI agents: 200+ countries of company data from official business registers. Search companies, get full firmographic records and look up exact city names. Hosted MCP, no install.

Tiktok Transcript Mcp

deapi-ai

Remote MCP server that transcribes public TikTok videos with an AI speech model. It listens to the audio rather than copying TikTok's auto-captions, so it works on videos that have no captions at all and across the 90+ l

広告掲載