Schema | Quant Framework MCP Server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`PERSONA`	Yes	The file path to the persona configuration YAML file (e.g., 'configs/persona.yaml'). Required for the 'serve' command.
`TRANSPORT`	No	The transport protocol to use for the MCP server. Options are 'stdio' or 'sse'. Use 'stdio' for standard MCP desktop integration.	sse
`FRED_API_KEY`	Yes	Your FRED API Key, obtained from FRED (Federal Reserve Economic Data). Required for the FRED connector to function.

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
run_linear	Fit a Linear Regression and return results with coefficients and residuals.
run_random_forest	Fit a Random Forest Regressor and return results with feature importances.
run_svr	Fit a Support Vector Regressor and return results.
run_xgboost	Fit an XGBoost Regressor and return results with feature importances.
run_bayesian_ridge	Fit a Bayesian Ridge Regression. Returns standard regression outputs plus Bayesian-specific posterior standard deviations and estimated precision parameters (alpha, lambda).
run_hmm	Fit a Gaussian Hidden Markov Model. `Unlike the regression functions, HMMs are unsupervised — there is no target column. The function discovers n_states hidden regimes in the data and returns the decoded state sequence, transition matrix, and per-state Gaussian parameters.`

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

Quant Framework MCP Server