{
  "markdown": "<div align=\"center\">\n\n# 🧠 Quant Brain MCP\n\n**Turn Claude into a quantitative analyst for US and Indian equities.**\n\nAsk in plain English. Get sized trade plans, portfolio optimization, backtests, and price alerts — grounded in real market data, not vibes.\n\n[![MCP Registry](https://img.shields.io/badge/MCP%20Registry-listed-0e6e5c)](https://registry.modelcontextprotocol.io/v0.1/servers?search=quant-brain-mcp)\n[![Tests](https://img.shields.io/badge/tests-161%20passing-0e6e5c)](tests/)\n[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)\n[![Python 3.12](https://img.shields.io/badge/python-3.12-blue.svg)](requirements.txt)\n\n</div>\n\n---\n\n```text\nYou:    \"Scan my watchlist and build a trade plan for whatever looks most actionable.\n         ₹2,00,000 equity, 1% risk.\"\n\nClaude: RELIANCE.NS flagged (at 20-DMA, volume 1.8x average).\n\n        TRADE PLAN — RELIANCE.NS (long)\n        Entry           ₹1,310.00\n        Stop            ₹1,270.10   (swing low, 2.1 ATR)\n        Size            50 shares   (₹65,500 — 32.8% of equity)\n        Max loss        ₹1,995      (1.0% of equity)\n        Targets         1R ₹1,349.90 · 2R ₹1,389.80 · 3R ₹1,429.70\n        Invalidation    Thesis invalid below ₹1,270.10 — exit without debate.\n```\n\nNo API keys. No accounts. Connect one URL and start asking.\n\n## ⚡ Quickstart\n\n**Claude Desktop / Claude Web** → Settings → Connectors → Add custom connector → **Streamable HTTP**:\n\n```text\nhttps://mcp-quant-brain.onrender.com/mcp\n```\n\nThat's the whole setup. Try: *\"What's RELIANCE trading at, and is it overbought?\"*\n\n> Free-tier note: the server sleeps when idle and takes ~50 s to wake. If the first request times out, retry once. Details in [Getting Started](docs/getting-started.md).\n\n## 🛠 What you get — 25 tools\n\n| | Tools | What they answer |\n|---|---|---|\n| 📋 **Trader workflow** | `get_quote` · `get_news` · `build_trade_plan` · `scan_watchlist` · `price_alert` | *What's it at? What happened? **What do I do?** What moved this week? Tell me when it hits my level.* |\n| 📊 **Indicators** | 6 grouped `analyze_*` tools — 38 curated indicators | *Is it overbought? Trending or chopping? How volatile?* |\n| 💼 **Portfolio** | `generate_optimized_verdict` — 7 optimization methods | *How do I split my money? What's my risk?* |\n| 🧪 **Backtests** | 7 rule-based strategies | *Does this strategy actually work, or does it just feel like it?* |\n| 🔭 **Intelligence** | Sector ranking · sector→stock pipeline · company profiles | *Which sector is leading? Which stocks inside it?* |\n| 📈 **Charts** | Institutional chart pack, rendered as images | *Show me.* |\n\nFull reference with every parameter: **[docs/tools.md](docs/tools.md)**\n\n## 🔄 The workflow it's built around\n\n```mermaid\nflowchart LR\n    S[\"🔍 <b>scan_watchlist</b><br/>what moved this week?\"] --> N[\"📰 <b>get_news</b><br/>why did it move?\"]\n    N --> P[\"📐 <b>build_trade_plan</b><br/>entry · stop · size · targets\"]\n    P --> A[\"🔔 <b>price_alert</b><br/>watch my levels\"]\n    A -.->|level breaks → notified| P\n    subgraph deeper[\"go deeper anytime\"]\n        I[\"📊 indicators\"] ~~~ B[\"🧪 backtests\"] ~~~ O[\"💼 optimizer\"]\n    end\n    S -.-> deeper\n```\n\n## 🔔 Price alerts that survive restarts\n\n```text\nYou:  \"Alert me if RELIANCE drops below ₹1,270\"        → stored server-side (Postgres)\n      ...\nBot:  \"PRICE ALERT FIRED — RELIANCE.NS moved below 1270.00, now at 1268.20\"\n```\n\nAlerts are one-shot, persist across server restarts, and pair with a scheduled Claude task that checks hourly during market hours and pushes to your phone. Setup in **[docs/price-alerts.md](docs/price-alerts.md)**.\n\n## 🎯 Why this instead of a stock screener?\n\n1. **It answers the trading question, not just the data question.** Indicators tell you RSI is 43. `build_trade_plan` tells you *entry, stop, how many shares, and where your thesis dies* — sized to your account.\n2. **India is a first-class citizen.** NSE tickers, NIFTY benchmarking, 8 Indian sector indices, ₹ formatting. Not a US tool with `.NS` bolted on.\n3. **The numbers are audited.** Every calculation was adversarially tested against textbook references and live data — 161 automated tests pin the math, including regression tests for 11 real bugs found and fixed along the way. See [docs/architecture.md](docs/architecture.md).\n4. **Honest about its data.** Delayed quotes are labeled with timestamps. Stale feeds are flagged, not hidden. FX limitations are disclosed, not papered over.\n\n## 📚 Documentation\n\n| Page | What's in it |\n|---|---|\n| [Getting Started](docs/getting-started.md) | Connecting from Claude Desktop, Web, and Code; cold starts; troubleshooting |\n| [Tool Reference](docs/tools.md) | All 25 tools, every parameter, response shapes |\n| [Example Prompts](docs/examples.md) | The prompt cookbook — from one-liners to full workflows |\n| [Price Alerts](docs/price-alerts.md) | Persistent alerts + the scheduled watcher pattern |\n| [Architecture & Methodology](docs/architecture.md) | How it works, data conventions, the bug audit, telemetry |\n\n## ⚠️ Honest limits\n\n- **Data**: Yahoo Finance. US quotes near-real-time; NSE/BSE ~15 min delayed. Daily bars for analysis.\n- **No** options chains, futures, intraday candles, or tick data.\n- **Not investment advice.** Educational analysis tooling. Every trade plan says so and means it.\n\n## License\n\n[MIT](LICENSE) — use it, fork it, ship it.\n",
  "bytes": 5386,
  "sha": "38bdcb834ddf420997c7c7efb502f4fdc96b67453877ed90bd3c1eb07458b56f",
  "repo_slug": "paarths-collab/quant-brain-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_paarths_collab_quant_brain_mcp_2a3166f7/readme"
}