dev.quantrisk/mcp-server

Official10 tools

by 78degrees · TypeScript

QuantRisk

Portfolio risk analytics — VaR, Monte Carlo, optimization, options Greeks, stress testing.

Calculate portfolio risk metrics including VaR, Monte Carlo, and options Greeks.

Captured live from the server via tools/list.

analyze_risk

Calculate core risk metrics for a portfolio — Value at Risk (VaR), Conditional VaR (CVaR), volatility, beta, and max drawdown.

Parameters (6)

positionsarrayrequired
Array of portfolio positions. Each entry needs a ticker and quantity. Free tier: max 20 positions. Paid tier: up to 500.
confidence_levelnumber
VaR confidence level as a decimal, e.g. 0.95 = 95%. Range: 0.01-0.99. Default: 0.95.
horizon_daysinteger
Risk horizon in trading days. 1 = overnight, 21 ≈ 1 month, 252 ≈ 1 year. Default: 1.
methodstring
VaR calculation method. "historical" uses empirical return distribution, "parametric" assumes normality, "cornish_fisher" adjusts for skew and kurtosis. Default: "historical".
benchmarkstring
Benchmark ticker for beta calculation, e.g. SPY or QQQ. Default: SPY.
lookback_daysinteger
Number of historical trading days to use. 252 ≈ 1 year, 756 ≈ 3 years. Range: 30-1260. Default: 252.

monte_carlo_simulation

Run Monte Carlo simulation on a portfolio to model the distribution of future returns, including percentile outcomes and probability of loss.

Parameters (6)

positionsarrayrequired
Array of portfolio positions. Free tier: max 20 positions. Paid tier: up to 500.
num_pathsinteger
Number of simulation paths to run. More paths = more accurate but slower. Free tier: max 1,000. Paid tier: up to 100,000. Default: 10,000.
horizon_daysinteger
Simulation horizon in trading days. 21 ≈ 1 month, 63 ≈ 1 quarter, 252 ≈ 1 year. Default: 21.
modelstring
Stochastic process model. "gbm" = Geometric Brownian Motion (standard), "jump_diffusion" = adds jump risk for fat-tail scenarios. Default: "gbm".
lookback_daysinteger
Historical window used to estimate drift and volatility parameters. Range: 30-1260 trading days. Default: 252.
seedany
Random seed for reproducible results. Omit for a fresh random run each time.

stress_test

Stress test a portfolio against historical crisis scenarios (GFC 2008, COVID 2020, etc.) or custom shocks (paid tier).

Parameters (3)

positionsarrayrequired
Array of portfolio positions. Free tier: max 20 positions and historical scenarios only. Paid tier: up to 500 positions plus custom shocks.
scenariosarray
Historical scenarios to run. Available values: gfc_2008, covid_2020, dot_com_2000, black_monday_1987, taper_tantrum_2013, rate_hike_2022, volmageddon_2018, euro_crisis_2011. Default: [gfc_2008, covid_2020].
custom_shocksany
Custom shock definitions. PAID tier only. Each shock specifies ticker-level, sector-level, or market-wide price changes.

optimize_portfolio

Find the optimal portfolio allocation using mean-variance optimization. Supports max Sharpe, min variance, and target return objectives. Paid tier only.

Parameters (6)

tickersarrayrequired
Universe of tickers to optimize across. Must be 2-50 tickers. The optimizer will determine the best weights within this set.
objectivestring
Optimization objective. "max_sharpe" = maximize risk-adjusted return, "min_variance" = minimize portfolio volatility, "target_return" = hit a specific return with minimum risk. Default: "max_sharpe".
target_returnany
Required when objective is "target_return". Annualized return as a decimal, e.g. 0.12 = 12% annual return target.
constraintsobject
Optional weight constraints. See ConstraintsInput for details.
risk_free_ratenumber
Annualized risk-free rate as a decimal, e.g. 0.05 = 5%. Used in Sharpe ratio calculation. Default: 0.05.
lookback_daysinteger
Historical window for estimating return and covariance. 252 = 1 year, 756 = 3 years, 1260 = 5 years. Range: 252-1260. Default: 756.

correlation_matrix

Compute the pairwise correlation matrix for a set of assets. Identifies highly correlated pairs and diversification opportunities.

Parameters (3)

tickersarrayrequired
Tickers to include in the correlation matrix. Minimum 2, maximum 50. Free tier: max 10 tickers. Paid tier: up to 50.
lookback_daysinteger
Historical window for computing correlations in trading days. 30 = ~6 weeks, 252 = ~1 year. Range: 30-1260. Default: 252.
methodstring
Correlation method. "pearson" = linear correlation (standard), "spearman" = rank-based (robust to outliers), "kendall" = concordance-based. Default: "pearson".

performance_attribution

Break down portfolio performance into factor exposures, sector allocation, and position contributions. Computes Sharpe, Sortino, Treynor, Calmar, and Information ratios.

Parameters (4)

positionsarrayrequired
Array of portfolio positions. Free tier: max 20 positions (basic ratios only). Paid tier: up to 500 positions with full factor attribution.
period_daysinteger
Measurement period in trading days. 252 = ~1 year. Range: 30-1260. Default: 252.
benchmarkstring
Benchmark ticker for relative performance metrics (Information Ratio, Tracking Error, Beta). Default: SPY.
risk_free_ratenumber
Annualized risk-free rate as a decimal, e.g. 0.05 = 5%. Used in Sharpe, Sortino, and Treynor ratios. Default: 0.05.

sector_exposure

Break down portfolio exposure by GICS sector, market cap, and asset class. Returns concentration metrics including the Herfindahl-Hirschman Index.

Parameters (1)

positionsarrayrequired
Array of portfolio positions to analyze. Returns GICS sector weights, market cap breakdown, and concentration metrics.

price_history

Fetch historical OHLCV price data for one or more tickers. Free tier: 1 ticker, 252 days. Paid tier: up to 20 tickers, 1260 days.

Parameters (3)

tickersarrayrequired
Ticker symbols to fetch price history for. Free tier: max 1 ticker. Paid tier: up to 20 tickers.
daysinteger
Number of historical trading days to return. Free tier: max 252 days (~1 year). Paid tier: up to 1260 days (~5 years). Default: 252.
intervalstring
Price interval. "daily" returns one OHLCV row per trading day, "weekly" aggregates to weekly bars, "monthly" aggregates to monthly bars. Default: "daily".

compare_portfolios

Compare two or more portfolio allocations head-to-head across all key risk and return metrics. Paid tier only.

Parameters (3)

portfoliosarrayrequired
Two to five named portfolios to compare head-to-head. Each needs a unique name and a list of positions. Min: 2, max: 5.
period_daysinteger
Lookback period in trading days used for return and risk calculations. 252 = ~1 year. Range: 30-1260. Default: 252.
confidence_levelnumber
VaR confidence level as a decimal, e.g. 0.95 = 95%. Range: 0.01-0.99. Default: 0.95.

calculate_greeks

Calculate option Greeks (delta, gamma, theta, vega, rho) for individual options or an options portfolio. Uses Black-Scholes for European, binomial for American style. Paid tier only.

Parameters (2)

optionsarrayrequired
Array of option positions to calculate Greeks for. 1-100 options. Results include per-option Greeks and aggregated portfolio Greeks.
risk_free_ratenumber
Annualized risk-free rate as a decimal, e.g. 0.05 = 5%. Used in Black-Scholes and binomial pricing models. Default: 0.05.

README.md6 KBView on GitHub

QuantRisk

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.

Website · Get Pro · Documentation

</div>

Quick Start

1. Install

bash

npm install -g @quantrisk/mcp-server

2. Configure (Claude Desktop — see below for Cursor)

Add to your claude_desktop_config.json:

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):

json

{
  "mcpServers": {
    "quantrisk": {
      "command": "quantrisk-mcp-server",
      "env": {
        "QUANTRISK_API_KEY": "your-api-key"
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json in your project root:

json

{
  "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.

Upgrade to Pro

How It Works

code

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.

bash

git clone https://github.com/78degrees/mcp-server.git
cd mcp-server
npm install
npm test

See CONTRIBUTING.md for guidelines.

License

MIT

Built by the team at quantrisk.dev

Contact: hello@quantrisk.dev

</div>

Install

Configuration

Environment variables

QUANTRISK_API_KEYsecret

API key from https://quantrisk.dev/upgrade. Optional — without one, requests run on the free tier (limited tools and call quotas).

claude_desktop_config.json

{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@quantrisk/mcp-server@1.0.2"
      ],
      "env": {
        "QUANTRISK_API_KEY": "<YOUR_QUANTRISK_API_KEY>"
      }
    }
  }
}