About QuantRisk
QuantRisk provides portfolio risk analytics for Claude and other MCP clients, calculating metrics with market data. It offers VaR, simulations, stress tests, and related analyses, with calculations handled by the QuantRisk API.
Key features
- 01VaR, CVaR, and volatility analysis
- 02Monte Carlo simulations and stress tests
- 03Asset correlations and sector exposure
- 04Portfolio optimization and comparison
- 05Options Greeks calculations
Use cases
- 01Assess portfolio VaR and maximum drawdown
- 02Simulate a portfolio’s potential return distribution
- 03Test the impact of historical crises or rate shocks
- 04Optimize allocations and analyze options Greeks
MCP support
The local MCP server connects to clients over stdio and sends analysis requests to the QuantRisk API. It exposes tools for portfolio risk, market data, and options analysis.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://quantrisk-mcp.quantrisk.workers.dev/mcpclaude mcp add --transport http dev-quantrisk https://quantrisk-mcp.quantrisk.workers.dev/mcp{"mcpServers":{"dev-quantrisk":{"type":"http","url":"https://quantrisk-mcp.quantrisk.workers.dev/mcp"}}}Open in Cursor{"servers":{"dev-quantrisk":{"type":"http","url":"https://quantrisk-mcp.quantrisk.workers.dev/mcp"}}}Open in VS Code{"mcpServers":{"dev-quantrisk":{"type":"http","url":"https://quantrisk-mcp.quantrisk.workers.dev/mcp"}}}{"mcpServers":{"dev-quantrisk":{"serverUrl":"https://quantrisk-mcp.quantrisk.workers.dev/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
10| Parameter | Type | Required | Description |
|---|---|---|---|
| method | enum | No | VaR calculation method. "historical" uses empirical return distribution, "parametric" assumes normality, "cornish_fisher" adjusts for skew and kurtosis. Default: "historical".historical | parametric | cornish_fisher |
| benchmark | string | No | Benchmark ticker for beta calculation, e.g. SPY or QQQ. Default: SPY. |
| positions | array | Yes | Array of portfolio positions. Each entry needs a ticker and quantity. Free tier: max 20 positions. Paid tier: up to 500. |
| horizon_days | integer | No | Risk horizon in trading days. 1 = overnight, 21 ≈ 1 month, 252 ≈ 1 year. Default: 1. |
| lookback_days | integer | No | Number of historical trading days to use. 252 ≈ 1 year, 756 ≈ 3 years. Range: 30-1260. Default: 252. |
| confidence_level | number | No | VaR confidence level as a decimal, e.g. 0.95 = 95%. Range: 0.01-0.99. Default: 0.95. |
Details
From the project READMEQuantRisk
Institutional-grade portfolio risk analytics for Claude and any MCP client.
VaR / Monte Carlo / Stress Testing / Portfolio Optimization / Greeks / Correlation Matrices
Real market data. Real math. Not hallucinated numbers.
Quick Start
1. Install
npm install -g @quantrisk/mcp-server
2. Configure (Claude Desktop — see below for Cursor)
Add to your claude_desktop_config.json:
{
"mcpServers": {
"quantrisk": {
"command": "quantrisk-mcp-server",
"env": {
"QUANTRISK_API_KEY": "your-api-key"
}
}
}
}
Get your free API key at quantrisk.dev/signup.
3. Ask Claude
"What's the Value at Risk on a portfolio of 60% SPY, 25% TLT, and 15% GLD?"
That's it. Claude now has access to institutional-grade risk analytics.
Configuration
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"quantrisk": {
"command": "quantrisk-mcp-server",
"env": {
"QUANTRISK_API_KEY": "your-api-key"
}
}
}
}
Cursor
Add to .cursor/mcp.json in your project root:
{
"mcpServers": {
"quantrisk": {
"command": "quantrisk-mcp-server",
"env": {
"QUANTRISK_API_KEY": "your-api-key"
}
}
}
}
Any MCP Client
QuantRisk works with any client that supports the Model Context Protocol. Point it at the quantrisk-mcp-server binary with your API key in the environment.
Tools
| Tool | Description | Tier |
|---|---|---|
analyze_risk | VaR, CVaR, volatility, Sharpe ratio, max drawdown | Free |
monte_carlo_simulation | Forward-looking return simulations with configurable paths | Free |
stress_test | Portfolio impact under historical and hypothetical scenarios | Free |
price_history | Historical price and return data for any supported ticker | Free |
sector_exposure | Sector and industry breakdown across holdings | Free |
performance_attribution | Return attribution by asset, sector, and factor | Free |
correlation_matrix | Cross-asset correlation analysis | Free |
optimize_portfolio | Mean-variance and risk-parity optimization | Pro |
compare_portfolios | Side-by-side risk/return comparison of multiple portfolios | Pro |
calculate_greeks | Options Greeks — delta, gamma, theta, vega, rho | Pro |
Example Queries
Once configured, ask Claude questions like these:
- "Run a Monte Carlo simulation on my portfolio: 50% AAPL, 30% MSFT, 20% NVDA. Show me the 5th percentile outcome."
- "Stress test 70% VTI / 30% BND against the 2008 financial crisis and a hypothetical 300bp rate shock."
- "What's my sector exposure if I hold equal weights in AMZN, JPM, JNJ, XOM, and NEE?"
- "Show me the correlation matrix for SPY, GLD, TLT, and BTC-USD over the last 2 years."
- "Compare the risk-adjusted returns of a 60/40 portfolio vs. an all-weather portfolio." (Pro)
- "Calculate the Greeks for a SPY 550 call expiring in 30 days." (Pro)
Why Pro?
The free tier covers core risk analytics for small portfolios. Pro unlocks the tools and scale that serious analysis demands.
| Free | Pro ($29/mo) | |
|---|---|---|
| Positions | 20 | 500 |
| API calls | 50/day | Unlimited |
| Tools | 7 | All 10 |
| Monte Carlo paths | 1,000 | 100,000 |
| Portfolio optimization | — | Mean-variance, risk-parity, min-volatility |
| Portfolio comparison | — | Side-by-side multi-portfolio analysis |
| Options Greeks | — | Full Greeks surface |
What that means in practice:
- Free: "What's the VaR on my 10-stock portfolio?" — works great.
- Pro: "Optimize my 200-position portfolio for maximum Sharpe, then stress test it against 5 scenarios and compare it to my current allocation." — you need Pro for that.
How It Works
Claude / MCP Client
|
MCP Protocol
|
QuantRisk MCP Server (local process)
|
QuantRisk API (Cloudflare Workers)
|
Yahoo Finance (market data) + risk engine (math)
- MCP Server runs locally as a stdio process — your API key never leaves your machine except to authenticate with the QuantRisk API.
- Risk Engine runs on Cloudflare Workers. All calculations — VaR, Monte Carlo, optimization — happen server-side with real math on real market data.
- Market Data sourced from Yahoo Finance. Prices, fundamentals, and options chains are fetched in real time.
- Reports generated with pdf-lib when applicable.
No data is stored. No portfolio information is retained after a request completes.
Contributing
Contributions are welcome. Please open an issue first to discuss what you'd like to change.
git clone https://github.com/78degrees/mcp-server.git
cd mcp-server
npm install
npm test
See CONTRIBUTING.md for guidelines.
License
Built by the team at quantrisk.dev
Contact: [email protected]
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.