RiskModels
Built for real portfolio work, not just descriptive analytics. Exposes dividend-adjusted total returns for roughly 16,000 US stocks (historical panel) plus daily factor decompositions, attribution, and ETF hedge ratios for the largest 3,000 by market cap. The model is hierarchical (market, sector, subsector) rather than flat beta, and hedge ratios are designed to work with liquid ETFs at execution time. Factor outputs run daily from 2007 forward, adjusted returns from 2006. Reach for this when you need time-safe risk decomposition or executable hedges tied to a real security master. The Python SDK handles ticker resolution and formats responses for LLM context. Ships with REST, typed SDKs, and stdio or streamable HTTP transports.
- tools
- 25
- transport
- STDIO, HTTP
- last updated
- Oct 15, 2026
Tools
25 toolsPublic tool metadata for what this MCP can expose to an agent.
riskmodels_get_stock_snapshot
No parameter schema in public metadata yet.
riskmodels_decompose
No parameter schema in public metadata yet.
riskmodels_compare
No parameter schema in public metadata yet.
riskmodels_get_returns
No parameter schema in public metadata yet.
riskmodels_get_return_attribution
No parameter schema in public metadata yet.
riskmodels_get_residual_returns
No parameter schema in public metadata yet.
riskmodels_get_residual_signal
No parameter schema in public metadata yet.
riskmodels_get_macro_correlation
No parameter schema in public metadata yet.
riskmodels_get_fundamentals
No parameter schema in public metadata yet.
riskmodels_analyze_portfolio
No parameter schema in public metadata yet.
riskmodels_get_portfolio_risk_snapshot
No parameter schema in public metadata yet.
riskmodels_portfolio_exposure
No parameter schema in public metadata yet.
riskmodels_decompose_selection_vs_drift
No parameter schema in public metadata yet.
riskmodels_get_my_positions
No parameter schema in public metadata yet.
riskmodels_get_rankings
No parameter schema in public metadata yet.
riskmodels_screen_rankings
No parameter schema in public metadata yet.
riskmodels_get_cohorts
No parameter schema in public metadata yet.
riskmodels_get_peers
No parameter schema in public metadata yet.
riskmodels_search
No parameter schema in public metadata yet.
riskmodels_resolve_security_identity
No parameter schema in public metadata yet.
riskmodels_get_filer
No parameter schema in public metadata yet.
riskmodels_get_fund
No parameter schema in public metadata yet.
riskmodels_get_etf
No parameter schema in public metadata yet.
riskmodels_get_benchmark_fit
No parameter schema in public metadata yet.
riskmodels_get_factor_returns
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
RiskModels provides clean dividend-adjusted total returns, factor risk decomposition, return attribution, and ETF-executable hedge ratios for US equities — over REST, a typed SDK, and a built-in MCP server. The dataset is simulation-grade: it covers on the order of 16,000 US stocks across the full historical panel, while at each month end the model’s headline universe is the largest ~3,000 by market cap—the set the API surfaces for everyday returns, risk, and hedging.
Post-regression outputs (hedge ratios, explained-risk decompositions, and related L1–L3 series) are served from the first date whose full estimation window is covered: hedge ratios from 2010-12-08, explained-risk shares and stock variance from 2011-12-07, L* residual levels from 2013-01-01. Split- and dividend-adjusted returns (the inputs to the rolling regressions) begin 2006-01-04. The API is AI-agent ready, including a built-in Model Context Protocol (MCP) server for seamless integration with LLMs.
RiskModels API Developer Portal
Details
- Repository
- github.com/bluewatercorp/riskmodels_api
- Website
- riskmodels.app
- Package
@riskmodels/mcp- Transport
- STDIO, HTTP
- Registry
- MCP registry, active