massive-com/mcp_massive

What it solves

This project provides a Model Context Protocol (MCP) server that allows Large Language Models (LLMs) to interact with the Massive.com financial data API. It solves the problem of manually mapping every single API endpoint to a tool, instead providing a few composable tools that give the LLM the ability to search for endpoints, call them, and query the resulting data using SQL.

How it works

The server acts as a bridge between an LLM and the Massive.com API. It provides three primary tools:

• search_endpoints: Allows the LLM to find the same API endpoints or built-in functions based on natural language queries.
• call_api: Executes REST API calls to Massive.com. It can store the results in an in-memory SQLite database table for further analysis.
• query_data: Enables the LLM to run SQL queries (including CTEs and window functions) against the stored SQLite data.

Additionally, the server includes built-in financial functions for calculating Greeks (Black-Scholes), returns (Sharpe ratio, Sortino ratio), and technical indicators (SMA, EMA).

Who it’s for

Developers and AI agents (like Claude Code or Claude Desktop) that need real-time and historical financial market data—including stocks, options, forex, crypto, and futures—integrated directly into their AI workflows.

Highlights

• Dynamic Indexing: Automatically stays in sync with the Massive.com API by indexing endpoints from an llms.txt file at startup.
• Composable Tooling: Uses a search-call-query pattern rather than a fixed list of tools.
• SQL Integration: Supports running complex SQL queries against API results stored in an in-memory database.
• Broad Financial Coverage: Accesses everything from real-time trades and quotes to analyst ratings, news, and Treasury yields.