Polygon.io MCP Server

Name: Polygon.io MCP Server
Author: polygon-io

@polygon-io

リポジトリ

Polygon.io MCP Server について

An MCP server for Massive.com Financial Market Data

#options #mcp #cryptocurrency #fintech #market-data #stocks #llm #mcp-server

基本情報

カテゴリ

金融とコマース

ライセンス

MIT

ランタイム

python

トランスポート

stdio

公開者

polygon-io

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": {
    "mcp_polygon": {
      "command": "uv",
      "args": [
        "tool",
        "install",
        "mcp_massive @ git+https://github.com/massive-com/[email protected]"
      ]
    }
  }
}

ツール

Search for API endpoints and built-in functions by natural language query. Returns titles, path patterns, and descriptions. Set `detail` to `"more"` for query parameter docs, or `"verbose"` for full documentation. Use `max_results` to limit results.

Call any Massive.com REST API endpoint. Supports storing results as an in-memory database table (`store_as`) and applying post-processing functions (`apply`). Paginated responses include a next-page hint.

Run SQL against stored SQLite DB. Supports `SHOW TABLES`, `DESCRIBE <table>`, `DROP TABLE <table>`, CTEs, window functions, and more. Results can also be post-processed with `apply`.

概要

What is Massive.com MCP Server?

The Massive.com MCP Server gives LLMs access to the full Massive.com financial data API through three composable tools: search, call, and query. Data can be stored in an in-memory SQLite database and enriched with built-in financial functions. It is for developers who want to integrate market data into AI assistants.

How to use Massive.com MCP Server?

Install with uv tool install "mcp_massive @ git+https://github.com/massive-com/[email protected]" and set the MASSIVE_API_KEY environment variable. Then register the server with Claude Code (claude mcp add massive...) or add it to your Claude Desktop configuration. The LLM uses three tools: search_endpoints to discover endpoints and functions, call_api to fetch data, and query_data to run SQL against stored results.

Key features of Massive.com MCP Server

Three tools cover the entire Massive.com API surface.
Built-in financial functions for Greeks, returns, and technicals.
Dynamic endpoint indexing via llms.txt stays current automatically.
In-memory SQLite database for storing and querying results.
Multiple transport options: stdio, SSE, and streamable-http.

Use cases of Massive.com MCP Server

Fetch real-time stock, option, forex, crypto, and futures aggregates.
Compute Black-Scholes option Greeks and moving averages.
Analyze historical trades, quotes, and market snapshots.
Retrieve financial fundamentals, dividends, splits, and analyst ratings.

FAQ from Massive.com MCP Server

What data does the server cover?

Stock, options, forex, crypto, and futures aggregates; real-time and historical trades and quotes; market snapshots, gainers/losers; ticker details; dividends, splits, IPOs; financial fundamentals; analyst ratings and news; treasury yields, inflation data; market status and holidays.

What are the prerequisites?

Python 3.12+, a Massive.com API key, and Astral UV v0.4.0+.

What environment variables are required?

MASSIVE_API_KEY is required. Optional: MCP_TRANSPORT (default stdio), MASSIVE_API_BASE_URL, MASSIVE_LLMS_TXT_URL, MASSIVE_MAX_TABLES (default 50), MASSIVE_MAX_ROWS (default 50000).

How does the server handle my API key?

The API key is used only for authenticating requests to Massive.com. No personal data is stored or cached; all requests are proxied directly.

What transport protocols are supported?

STDIO by default. SSE and streamable-http are also supported via the --transport CLI argument or MCP_TRANSPORT environment variable.

「金融とコマース」の他のコンテンツ

Armor Crypto MCP

armorwallet

The MCP server for interacting with Blockchain, Swaps, Strategic Planning and more.

181

MetaTrader 5 MCP Server

Qoyyuum

A Model Context Protocol (MCP) server for interacting with the MetaTrader 5 trading platform. This server provides AI assistants with tools and resources to access market data, perform trading operations, and analyze trading history.

187