A Model Context Protocol (MCP) server that provides access to the full Massive.com financial data API through an LLM-friendly interface. Rather than exposing one tool per endpoint, this server gives the LLM four composable tools — search, docs, call, and query — that cover the entire Massive.com API surface. Data can be stored in-memory as DataFrames, queried with SQL, and enriched with built-in f
Add this skill
npx mdskills install massive-com/mcp-massiveWell-architected MCP server providing composable financial data access with SQL querying and analytics
Important:
:test_tube: This project is experimental and could be subject to breaking changes.
A Model Context Protocol (MCP) server that provides access to the full Massive.com financial data API through an LLM-friendly interface.
Rather than exposing one tool per endpoint, this server gives the LLM four composable tools — search, docs, call, and query — that cover the entire Massive.com API surface. Data can be stored in-memory as DataFrames, queried with SQL, and enriched with built-in financial functions.
| Tool | Description |
|---|---|
search_endpoints | Search for API endpoints and built-in functions by natural language query. Returns names, URL patterns, and descriptions. Supports scoping to endpoints, functions, or all. |
get_endpoint_docs | Get parameter documentation for a specific endpoint. Pass the docs URL from search_endpoints results. |
call_api | Call any Massive.com REST API endpoint. Supports storing results as an in-memory DataFrame (store_as) and applying post-processing functions (apply). Paginated responses include a next-page hint. |
query_data | Run SQL against stored DataFrames using SQLite. Supports SHOW TABLES, DESCRIBE , DROP TABLE , CTEs, window functions, and more. Results can also be post-processed with apply. |
Functions can be applied to API results or query output via the apply parameter on call_api and query_data. Use search_endpoints with scope="functions" to discover them.
| Category | Functions |
|---|---|
| Greeks | bs_price, bs_delta, bs_gamma, bs_theta, bs_vega, bs_rho — Black-Scholes option pricing and greeks |
| Returns | simple_return, log_return, cumulative_return, sharpe_ratio, sortino_ratio |
| Technical | sma (simple moving average), ema (exponential moving average) |
The server dynamically indexes all Massive.com API endpoints at startup from llms.txt, so it automatically stays in sync with the API. Coverage includes:
First, install Claude Code
npm install -g @anthropic-ai/claude-code
Install the MCP server, then register it with Claude Code:
# Install the server (one-time — downloads dependencies ahead of time)
uv tool install "mcp_massive @ git+https://github.com/massive-com/mcp_massive@v0.8.1"
# Register with Claude Code
claude mcp add massive -e MASSIVE_API_KEY=your_api_key_here -- mcp_massive
To upgrade to a new version later:
uv tool upgrade mcp_massive
Note:
Upgrading from
uvxoruv run --with? Previous versions recommendeduvx --from ... mcp_massiveoruv run --with. These commands download dependencies on every cold start, which can cause the server to exceed Claude's 30-second connection timeout. Switch touv tool installas shown above — it downloads dependencies once and starts instantly after that.
This command will install the MCP server in your current project.
If you want to install it globally, you can run the command with -s flag.
See claude mcp add --help for more options.
To start Claude Code, run claude in your terminal.
You can also run claude mcp add-from-claude-desktop if the MCP server is installed already for Claude Desktop.
uv tool install "mcp_massive @ git+https://github.com/massive-com/mcp_massive@v0.8.1"
# Mac/Linux
which mcp_massive
# Windows
where mcp_massive
claude_desktop_config.json
{
"mcpServers": {
"massive": {
"command": "",
"env": {
"MASSIVE_API_KEY": "",
"HOME": ""
}
}
}
}
| Variable | Required | Default | Description |
|---|---|---|---|
MASSIVE_API_KEY | Yes | — | Your Massive.com API key |
POLYGON_API_KEY | No | — | Deprecated alias for MASSIVE_API_KEY |
MCP_TRANSPORT | No | stdio | Transport protocol: stdio, sse, or streamable-http |
MASSIVE_API_BASE_URL | No | https://api.massive.com | Base URL for API requests |
MASSIVE_LLMS_TXT_URL | No | https://massive.com/docs/rest/llms.txt | URL for the endpoint index |
MASSIVE_MAX_TABLES | No | 50 | Maximum number of in-memory DataFrames |
MASSIVE_MAX_ROWS | No | 50000 | Maximum rows per stored DataFrame |
By default, STDIO transport is used. The transport can be set via the --transport CLI argument or the MCP_TRANSPORT environment variable (CLI argument takes precedence).
# CLI argument
MASSIVE_API_KEY= uv run mcp_massive --transport streamable-http
# Environment variable
MCP_TRANSPORT=streamable-http MASSIVE_API_KEY= uv run mcp_massive
Once integrated, you can prompt Claude to access Massive.com data:
Get the latest price for AAPL stock
Show me yesterday's trading volume for MSFT
What were the biggest stock market gainers today?
Get me the latest crypto market data for BTC-USD
Calculate the 20-day SMA for AAPL closing prices over the last 3 months
Compute Black-Scholes delta for these option contracts
Check to ensure you have the Prerequisites installed.
# Sync dependencies
uv sync
# Run the server
MASSIVE_API_KEY=your_api_key_here uv run mcp_massive
Local Dev Config for claude_desktop_config.json
Install from your local checkout, then reference the binary directly:
uv tool install --force /path/to/mcp_massive
{
"mcpServers": {
"massive": {
"command": "mcp_massive",
"env": {
"MASSIVE_API_KEY": "your_api_key_here"
}
}
}
}
For debugging and testing, we recommend using the MCP Inspector:
npx @modelcontextprotocol/inspector uv --directory /path/to/mcp_massive run mcp_massive
This will launch a browser interface where you can interact with your MCP server directly and see input/output for each tool.
This project uses just for common development tasks. To lint your code before submitting a PR:
just lint
This will run ruff format and ruff check --fix to automatically format your code and fix linting issues.
This MCP server interacts with Massive.com's API to fetch market data. All data requests are subject to Massive.com's privacy policy and terms of service.
If you found a bug or have an idea for a new feature, please first discuss it with us by submitting a new issue. We will respond to issues within at most 3 weeks. We're also open to volunteers if you want to submit a PR for any open issues but please discuss it with us beforehand. PRs that aren't linked to an existing issue or discussed with us ahead of time will generally be declined.
Install via CLI
npx mdskills install massive-com/mcp-massiveMassive.com MCP Server is a free, open-source AI agent skill. A Model Context Protocol (MCP) server that provides access to the full Massive.com financial data API through an LLM-friendly interface. Rather than exposing one tool per endpoint, this server gives the LLM four composable tools — search, docs, call, and query — that cover the entire Massive.com API surface. Data can be stored in-memory as DataFrames, queried with SQL, and enriched with built-in f
Install Massive.com MCP Server with a single command:
npx mdskills install massive-com/mcp-massiveThis downloads the skill files into your project and your AI agent picks them up automatically.
Massive.com MCP Server works with Claude Code, Claude Desktop, Cursor, Vscode Copilot, Windsurf, Continue Dev, Gemini Cli, Amp, Roo Code, Goose. Skills use the open SKILL.md format which is compatible with any AI coding agent that reads markdown instructions.