{
  "markdown": "<div align=\"center\">\n\n# QuantRisk\n\n**Institutional-grade portfolio risk analytics for Claude and any MCP client.**\n\n[![npm version](https://img.shields.io/npm/v/@quantrisk/mcp-server.svg)](https://www.npmjs.com/package/@quantrisk/mcp-server)\n[![npm downloads](https://img.shields.io/npm/dm/@quantrisk/mcp-server.svg)](https://www.npmjs.com/package/@quantrisk/mcp-server)\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)\n[![MCP Compatible](https://img.shields.io/badge/MCP-compatible-brightgreen.svg)](https://modelcontextprotocol.io)\n\nVaR / Monte Carlo / Stress Testing / Portfolio Optimization / Greeks / Correlation Matrices\n\nReal market data. Real math. Not hallucinated numbers.\n\n[Website](https://quantrisk.dev) · [Get Pro](https://quantrisk.dev/pricing) · [Documentation](https://quantrisk.dev/docs)\n\n</div>\n\n---\n\n## Quick Start\n\n**1. Install**\n\n```bash\nnpm install -g @quantrisk/mcp-server\n```\n\n**2. Configure** (Claude Desktop — see [below](#configuration) for Cursor)\n\nAdd to your `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"quantrisk\": {\n      \"command\": \"quantrisk-mcp-server\",\n      \"env\": {\n        \"QUANTRISK_API_KEY\": \"your-api-key\"\n      }\n    }\n  }\n}\n```\n\nGet your free API key at [quantrisk.dev/signup](https://quantrisk.dev/signup).\n\n**3. Ask Claude**\n\n> \"What's the Value at Risk on a portfolio of 60% SPY, 25% TLT, and 15% GLD?\"\n\nThat's it. Claude now has access to institutional-grade risk analytics.\n\n---\n\n## Configuration\n\n### Claude Desktop\n\nAdd to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\\Claude\\claude_desktop_config.json` (Windows):\n\n```json\n{\n  \"mcpServers\": {\n    \"quantrisk\": {\n      \"command\": \"quantrisk-mcp-server\",\n      \"env\": {\n        \"QUANTRISK_API_KEY\": \"your-api-key\"\n      }\n    }\n  }\n}\n```\n\n### Cursor\n\nAdd to `.cursor/mcp.json` in your project root:\n\n```json\n{\n  \"mcpServers\": {\n    \"quantrisk\": {\n      \"command\": \"quantrisk-mcp-server\",\n      \"env\": {\n        \"QUANTRISK_API_KEY\": \"your-api-key\"\n      }\n    }\n  }\n}\n```\n\n### Any MCP Client\n\nQuantRisk works with any client that supports the [Model Context Protocol](https://modelcontextprotocol.io). Point it at the `quantrisk-mcp-server` binary with your API key in the environment.\n\n---\n\n## Tools\n\n| Tool | Description | Tier |\n|------|-------------|------|\n| `analyze_risk` | VaR, CVaR, volatility, Sharpe ratio, max drawdown | Free |\n| `monte_carlo_simulation` | Forward-looking return simulations with configurable paths | Free |\n| `stress_test` | Portfolio impact under historical and hypothetical scenarios | Free |\n| `price_history` | Historical price and return data for any supported ticker | Free |\n| `sector_exposure` | Sector and industry breakdown across holdings | Free |\n| `performance_attribution` | Return attribution by asset, sector, and factor | Free |\n| `correlation_matrix` | Cross-asset correlation analysis | Free |\n| `optimize_portfolio` | Mean-variance and risk-parity optimization | **Pro** |\n| `compare_portfolios` | Side-by-side risk/return comparison of multiple portfolios | **Pro** |\n| `calculate_greeks` | Options Greeks — delta, gamma, theta, vega, rho | **Pro** |\n\n---\n\n## Example Queries\n\nOnce configured, ask Claude questions like these:\n\n- **\"Run a Monte Carlo simulation on my portfolio: 50% AAPL, 30% MSFT, 20% NVDA. Show me the 5th percentile outcome.\"**\n- **\"Stress test 70% VTI / 30% BND against the 2008 financial crisis and a hypothetical 300bp rate shock.\"**\n- **\"What's my sector exposure if I hold equal weights in AMZN, JPM, JNJ, XOM, and NEE?\"**\n- **\"Show me the correlation matrix for SPY, GLD, TLT, and BTC-USD over the last 2 years.\"**\n- **\"Compare the risk-adjusted returns of a 60/40 portfolio vs. an all-weather portfolio.\"** *(Pro)*\n- **\"Calculate the Greeks for a SPY 550 call expiring in 30 days.\"** *(Pro)*\n\n---\n\n## Why Pro?\n\nThe free tier covers core risk analytics for small portfolios. Pro unlocks the tools and scale that serious analysis demands.\n\n| | Free | Pro ($29/mo) |\n|---|---|---|\n| **Positions** | 20 | 500 |\n| **API calls** | 50/day | Unlimited |\n| **Tools** | 7 | All 10 |\n| **Monte Carlo paths** | 1,000 | 100,000 |\n| **Portfolio optimization** | — | Mean-variance, risk-parity, min-volatility |\n| **Portfolio comparison** | — | Side-by-side multi-portfolio analysis |\n| **Options Greeks** | — | Full Greeks surface |\n\n**What that means in practice:**\n\n- Free: \"What's the VaR on my 10-stock portfolio?\" — works great.\n- 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.\n\n[Upgrade to Pro](https://quantrisk.dev/pricing)\n\n---\n\n## How It Works\n\n```\nClaude / MCP Client\n      |\n  MCP Protocol\n      |\nQuantRisk MCP Server (local process)\n      |\nQuantRisk API (Cloudflare Workers)\n      |\nYahoo Finance (market data) + risk engine (math)\n```\n\n- **MCP Server** runs locally as a stdio process — your API key never leaves your machine except to authenticate with the QuantRisk API.\n- **Risk Engine** runs on Cloudflare Workers. All calculations — VaR, Monte Carlo, optimization — happen server-side with real math on real market data.\n- **Market Data** sourced from Yahoo Finance. Prices, fundamentals, and options chains are fetched in real time.\n- **Reports** generated with pdf-lib when applicable.\n\nNo data is stored. No portfolio information is retained after a request completes.\n\n---\n\n## Contributing\n\nContributions are welcome. Please open an issue first to discuss what you'd like to change.\n\n```bash\ngit clone https://github.com/78degrees/mcp-server.git\ncd mcp-server\nnpm install\nnpm test\n```\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.\n\n---\n\n## License\n\n[MIT](LICENSE)\n\n---\n\n<div align=\"center\">\n\nBuilt by the team at [quantrisk.dev](https://quantrisk.dev)\n\nContact: hello@quantrisk.dev\n\n</div>\n",
  "bytes": 5928,
  "sha": "d1b65f0c7cd93d432933635e14158bd2804fb7ff2ba14d42380c7eaad70ae3fc",
  "repo_slug": "78degrees/mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_78degrees_quantrisk_fbceb7a5/readme"
}