# @riskmodels/mcp

MCP server for RiskModels: clean dividend-adjusted US equity total returns, risk decomposition, factor/residual return attribution, and ETF hedge ratios

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the package rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 2.0.1
- **Author:** io.github.BlueWaterCorp
- **License:** Unknown
- **npm:** @riskmodels/mcp
- **Endpoints:** streamable-http https://riskmodels.app/api/mcp/sse
- **Source:** https://github.com/BlueWaterCorp/RiskModels_API
- **Endpoint health:** reachable (last checked 2026-10-17T15:29:09.420Z, 1 sample) — uptime is not a security property and is not part of the trust score
- **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport)

## Trust

60/100 (B), scored on the package rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 0 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-10-20T09:59:24.831Z
- **Version scanned:** 2.0.1
- **CVEs:** none found by OSV at scan time

## Tools

24 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `riskmodels_get_stock_snapshot`
- `riskmodels_decompose`
- `riskmodels_compare` — Use when you want 2-100 stocks side by side on market, sector, subsector and residual risk. Not for one stock (use riskmodels_decompose) or a weighted portfolio
- `riskmodels_get_returns`
- `riskmodels_get_return_attribution`
- `riskmodels_get_residual_returns`
- `riskmodels_get_residual_signal` — Use when you want the L3 residual mean-reversion signal aggregated over a basket of 1-100 stocks. Not for the residual return series themselves (use riskmodels_
- `riskmodels_get_macro_correlation` — Use when you want to know how one stock's returns co-move with macro factors such as rates, credit, oil, the dollar or volatility. Not for the macro factor retu
- `riskmodels_get_fundamentals`
- `riskmodels_analyze_portfolio`
- `riskmodels_get_portfolio_risk_snapshot`
- `riskmodels_portfolio_exposure`
- `riskmodels_decompose_selection_vs_drift`
- `riskmodels_get_my_positions`
- `riskmodels_get_rankings` — Use when you want one stock's percentile rank within the universe, its sector or its subsector on a risk or return metric. Not for screening the whole universe 
- `riskmodels_screen_rankings` — Use when you want the names in the universe that rank highest or lowest on one metric, with optional percentile, decile and sector filters. Not for one stock's 
- `riskmodels_get_cohorts`
- `riskmodels_get_peers` — Use when you want the stocks that share a stock's subsector ETF or sector ETF. Not for cohort-level residual statistics (use riskmodels_get_cohorts). Returns, f
- `riskmodels_search`
- `riskmodels_get_filer`
- `riskmodels_get_fund`
- `riskmodels_get_etf` — Use when you want one ETF's registry metadata and portfolio surface, and optionally its largest holdings. Not for finding an ETF ticker (use riskmodels_search) 
- `riskmodels_get_benchmark_fit`
- `riskmodels_get_factor_returns`

## Install

**Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for.
**Cautions** (coverage gaps and advisories — never blocking)
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@riskmodels/mcp\"\n      ]\n    }\n  }\n}"
```

## Blast radius

Contained to extensive — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs locally and hosted; read-only tool surface.
- Floor 17, ceiling 35 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/%40riskmodels%2Fmcp
- Install plan: https://forgeregistry.com/api/v1/packages/%40riskmodels%2Fmcp/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/%40riskmodels%2Fmcp
- HTML page: https://forgeregistry.com/registry/%40riskmodels%2Fmcp
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.