Skip to main content
Glama
Epsom700

Quant Framework MCP Server

by Epsom700
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PERSONAYesThe file path to the persona configuration YAML file (e.g., 'configs/persona.yaml'). Required for the 'serve' command.
TRANSPORTNoThe transport protocol to use for the MCP server. Options are 'stdio' or 'sse'. Use 'stdio' for standard MCP desktop integration.sse
FRED_API_KEYYesYour FRED API Key, obtained from FRED (Federal Reserve Economic Data). Required for the FRED connector to function.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
run_linearC

Fit a Linear Regression and return results with coefficients and residuals.

run_random_forestC

Fit a Random Forest Regressor and return results with feature importances.

run_svrC

Fit a Support Vector Regressor and return results.

run_xgboostB

Fit an XGBoost Regressor and return results with feature importances.

run_bayesian_ridgeB

Fit a Bayesian Ridge Regression.

Returns standard regression outputs plus Bayesian-specific posterior standard deviations and estimated precision parameters (alpha, lambda).

run_hmmA

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.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.4/5.0

Scored across 6 tools

Disambiguation5/5

Every tool has a clearly distinct purpose with no ambiguity - each implements a different machine learning algorithm (Bayesian Ridge, HMM, Linear Regression, Random Forest, SVR, XGBoost). The descriptions clearly differentiate between supervised regression methods and the unsupervised HMM approach.

Naming Consistency5/5

Perfect naming consistency with all tools following the exact same 'run_algorithm' pattern. The naming convention is completely uniform across all six tools, making them easily predictable and readable.

Tool Count5/5

Six tools is well-scoped for a quant framework server focused on statistical modeling algorithms. Each tool earns its place by covering different modeling approaches (linear, tree-based, Bayesian, HMM, SVM, gradient boosting) without redundancy.

Completeness4/5

The toolset covers a comprehensive range of regression and time series modeling algorithms appropriate for quantitative analysis. Minor gaps might include clustering algorithms or additional preprocessing tools, but the core modeling surface is well-covered for a quant framework.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources