search_endpointsLABSCO SUMMARY
The whole API behind three tools, plus a SQL scratchpad.
One tool per endpoint fills a model's context with definitions it will never call. Search-then-call keeps that near zero, and storing results as SQLite turns the follow-up question into a query rather than another fetch.
What it is
An MCP server over a full financial-data REST API. Rather than one tool per endpoint it gives the model search, call and query: find the endpoint, call it, optionally store the result as an in-memory SQLite table, then run SQL against that. The endpoint index is built at startup from the API's llms.txt.
What you get
- Endpoints and built-in functions found by natural-language query, at three levels of detail
- Any REST endpoint called, with paginated responses carrying a next-page hint
- Results stored as an in-memory SQLite table for later querying
- SQL run over stored tables, including SHOW TABLES, DESCRIBE, CTEs and window functions
- Black-Scholes pricing and greeks applied to results: bs_price, bs_delta, bs_gamma, bs_theta, bs_vega, bs_rho
- Return and risk functions: simple_return, log_return, cumulative_return, sharpe_ratio, sortino_ratio
- Moving averages: sma and ema
Requirements
An API key for the data provider. The project is marked experimental and subject to breaking changes, so pin the version if you build on it.
Setup effort
One command plus a key — uv tool install "mcp_massive @ git+https://github.com/massive-com/mcp_massive@v0.10.0", then supply credentials
USE CASES
01
Finding the endpoint you need without reading the docs
Describe what you are after in words and get back matching endpoints with their path patterns and parameter documentation.
02
Pulling a series and then asking a follow-up about it
Store the response as a table, then answer the next three questions in SQL instead of three more API calls.
03
Joining two datasets the API returns separately
Store both as tables and join them locally with a single query.
04
Pricing an option and getting its greeks
Apply the Black-Scholes functions to the result of the call, in the same request.
05
Comparing risk-adjusted returns across tickers
Fetch the price history, store it, and run the return and ratio functions over the stored table.
3 tools
Listed in project docs. Your client may show a different list.
call_apiquery_dataBEFORE YOU INSTALL
What to know first
Tools you get
3 tools named in the project's documentation.
Requires
- mcp_massive on PATH
- Python 3.12+
- MASSIVE_API_KEY in your environment
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
uv tool install "mcp_massive @ git+https://github.com/massive-com/mcp_massive@v0.10.0"MCP Clients
Claude Code
CLAUDE CODE · TERMINAL
claude mcp add massive -e MASSIVE_API_KEY=<YOUR_MASSIVE_API_KEY> -- mcp_massiveClaude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"massive": {
"command": "<YOUR_PATH_TO_MCP_MASSIVE>",
"env": {
"MASSIVE_API_KEY": "<YOUR_MASSIVE_API_KEY>",
"HOME": "<YOUR_HOME>"
}
}
}
}
