Riskmodels

Name: Riskmodels
Author: BlueWaterCorp

@BlueWaterCorp

About Riskmodels

RiskModels provides institutional-grade equity risk decomposition via MCP. Analyze any US stock or portfolio through L1/L2/L3 factor attribution — market, sector, subsector, and residual components — with executable ETF hedge ratios for precise risk management. Built for portfoli

#finance #trading #risk-management #portfolio-analysis #equities #etf #hedging #quantitative #mcp #api

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "riskmodels": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli@latest",
        "run",
        "service-c09f/riskmodels"
      ],
      "env": {
        "SMITHERY_API_KEY": "<your-smithery-api-key>"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is RiskModels?

RiskModels provides clean dividend-adjusted total returns, factor risk decomposition, return attribution, and ETF-executable hedge ratios for US equities. It is delivered over REST, a typed Python SDK, and a built-in MCP (Model Context Protocol) server. The dataset covers ~16,000 US stocks historically, with a monthly headline universe of the largest ~3,000 by market cap.

How to use RiskModels?

Install the Python SDK with pip install riskmodels-py, then create a RiskModelsClient and call methods like client.analyze(). For AI agent integration, connect to the hosted MCP server via SSE at https://riskmodels.app/api/mcp/sse or run the local MCP server with stdio transport for tools like riskmodels_decompose and riskmodels_hedge_position. A CLI tool is also available via npm.

Key features of RiskModels

Daily factor decompositions for market, sector, and subsector
Dollar-denominated ETF hedge ratios (L1/L2/L3) for liquid ETFs
Historical split- and dividend-adjusted returns from 2006-01-04
Built-in MCP server for AI agent and LLM integration
Python SDK with agent-native helpers and LLM-ready context formatting
OAuth2 authentication and per-request billing

Use cases of RiskModels

Decompose portfolio risk into market, sector, and subsector components
Obtain executable hedge ratios for individual US equity positions
Perform return attribution for a universe of ~3,000 US stocks
Integrate factor risk analysis directly into AI agent workflows via MCP

FAQ from RiskModels

What data coverage does RiskModels offer?

The historical panel covers ~16,000 US stocks. The monthly headline universe for daily outputs is the largest ~3,000 stocks by market cap. Split- and dividend-adjusted returns are available from 2006-01-04; factor outputs (hedge ratios and explained risk) begin in 2007.

How do I connect an AI agent to RiskModels?

Use the hosted MCP server’s SSE endpoint at https://riskmodels.app/api/mcp/sse with a Bearer token (API key or OAuth2 JWT). Alternatively, run the local MCP server from this repository for stdio transport, which exposes tools like riskmodels_decompose and riskmodels_hedge_position.

What authentication options are available?

The API supports OAuth2 and bearer token authentication using an API key. API keys can be obtained from the developer portal at riskmodels.app/get-key.

Are the hedge ratios designed for actual trading?

Yes. The published L1/L2/L3 hedge ratios are dollar-denominated and designed to remain executable with liquid raw ETFs, not with synthetic or orthogonalized factors.

What are the historical data start dates?

Adjusted return series begin on 2006-01-04. Factor outputs (hedge ratios and explained risk) are available from 2007 through present. Daily updates are applied.