Mmcp.market

Quant Brain MCP server

by paarths-collab·io.github.paarths-collab/quant-brain-mcp·v1.0.0
No reviews yet

Stock analysis MCP: 38 indicators, 7 optimizers, 8 backtests, US + India sectors.

B77/100grade B
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
B77/100

full report

Adoption
Growing

4 stars

Reviews

Write one

Nobody has reviewed Quant Brain yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Quant Brain tools (25, 8 write)

write = sends, deletes, buys or posts
  • analyze_momentumFree

    Momentum indicators: rsi, macd, roc, cci, stoch, stochrsi, tsi, willr. Runs all momentum indicators for the ticker, or only the subset named in `indicators` (e.g. ["rsi", "macd"]). `period` sets the history window: "1d","5d","1mo","3mo","6mo","1y","2y","5y","10y","ytd","max" (default "2y").

  • analyze_sector_intelligence_toolFree

    Analyze sector return, risk, momentum, drawdown and correlation; select best sector.

  • analyze_statisticsFree

    Statistical behavior: log_return, zscore, skew, kurtosis, entropy. Runs all statistical indicators for the ticker, or only the subset named in `indicators`. `period` sets the history window: "1d","5d","1mo","3mo", "6mo","1y","2y","5y","10y","ytd","max" (default "2y").

  • analyze_technical_levelsFree

    Moving averages and price levels: sma, ema, hma, kama, ichimoku, supertrend, vwap, vwma. Runs all level indicators for the ticker, or only the subset named in `indicators`. `period` sets the history window: "1d","5d","1mo","3mo", "6mo","1y","2y","5y","10y","ytd","max" (default "2y").

  • analyze_trendFree

    Trend strength and direction: adx, aroon, chop, psar, vortex, zigzag. Runs all trend indicators for the ticker, or only the subset named in `indicators`. `period` sets the history window: "1d","5d","1mo","3mo", "6mo","1y","2y","5y","10y","ytd","max" (default "2y").

  • analyze_volatilityFree

    Volatility and bands: atr, bbands, donchian, kc, stdev, ui. Runs all volatility indicators for the ticker, or only the subset named in `indicators`. `period` sets the history window: "1d","5d","1mo","3mo", "6mo","1y","2y","5y","10y","ytd","max" (default "2y").

  • analyze_volumeFree

    Volume confirmation: obv, cmf, mfi, ad, pvt. Runs all volume indicators for the ticker, or only the subset named in `indicators`. `period` sets the history window: "1d","5d","1mo","3mo", "6mo","1y","2y","5y","10y","ytd","max" (default "2y").

  • backtest_macd_momentumwrite actionFree

    Run MACD momentum strategy backtest for one ticker. `period`: history window, e.g. "1y","2y","5y","10y" (default "2y").

  • backtest_macd_trend_followerwrite actionFree

    Run MACD trend follower strategy backtest for one ticker. `period`: history window, e.g. "1y","2y","5y","10y" (default "2y").

  • backtest_mean_reversion_rsi_bbwrite actionFree

    Run RSI + Bollinger Band mean-reversion strategy backtest. `period`: history window, e.g. "1y","2y","5y","10y" (default "2y").

  • backtest_rsi_mean_reversionwrite actionFree

    Run RSI mean-reversion strategy backtest. `period`: history window, e.g. "1y","2y","5y","10y" (default "2y").

  • backtest_sma_crossoverwrite actionFree

    Run SMA crossover strategy backtest. `period`: history window, e.g. "1y","2y","5y","10y" (default "2y").

  • backtest_trend_crossoverwrite actionFree

    Run trend crossover strategy backtest. `period`: history window, e.g. "1y","2y","5y","10y" (default "2y").

  • backtest_volatility_breakoutwrite actionFree

    Run volatility breakout strategy backtest. `period`: history window, e.g. "1y","2y","5y","10y" (default "2y").

  • build_trade_planFree

    Build a sized trade plan: entry, stop, share count, R targets, invalidation. The answer to "what do I do?": given account equity and the percent of it you are willing to risk, returns an entry reference (last close), a structural stop (tighter of recent swing level or 2x ATR, never inside daily noise), the exact number of shares so a stop-out loses only the risk budget, 1R/2R/3R targets, a liquidity check (order as % of 20-day turnover), and a one-line invalidation. Educational analysis, not investment advice.

  • find_sector_stock_pipeline_toolwrite actionFree

    Run a multi-step pipeline: sector performance -> stock ranking -> strategy selection.

  • generate_chart_packFree

    Generate the full institutional chart suite for dashboard rendering.

  • generate_chartsFree

    Generate charts for portfolio, strategy, quant, fundamentals, and sector pipeline.

  • generate_optimized_verdictFree

    Optimize a portfolio and return backtest metrics plus a final verdict. Args: tickers: List of ticker symbols (e.g. ["AAPL", "RELIANCE.NS"]) amount: Investment amount used for allocation context optimize_type: Optimization mode. Supported values are: "mvo", "hrp", "max_sharpe", "min_volatility", "black_litterman", "cvar", "semivariance". period: History window for price data, e.g. "1y", "2y", "5y", "10y" (default "2y"). Longer windows give the optimizer and backtest more data at the cost of a slower fetch.

  • get_company_profileFree

    Return a full company snapshot with business, valuation, and market metadata.

  • get_newsFree

    Recent news headlines for a ticker via Yahoo Finance's news feed. Returns structured articles (title, publisher, url, published_at, summary) for you to read and synthesize. Not a scraper -- uses Yahoo's aggregated feed, so coverage is strongest for large-cap US and Indian names.

  • get_quoteFree

    Current price snapshot for one or more tickers (US and Indian). Returns last price, day change %, day and 52-week ranges, position within the 52-week range, and volume vs 3-month average, with an `as_of` timestamp. US quotes are near-real-time; NSE/BSE quotes are ~15 minutes delayed (disclosed in the response). For to-the-second Indian prices during market hours, supplement with a live web search.

  • plot_chartsFree

    Alias for chart generation; kept for natural plotting language in clients.

  • price_alertFree

    Persistent price alerts stored server-side (survive restarts, one-shot). Actions: set -- watch a level: price_alert("set", ticker="RELIANCE.NS", level=1270, direction="below", note="stop level") list -- show all active alerts delete -- remove an alert by alert_id check -- fetch current prices for every active alert and return which fired; fired alerts deactivate so they never spam. A server cannot push messages into Claude, so pair this with a scheduled task that calls action='check' on a cadence (e.g. every 30 minutes during market hours) and notifies the user only when 'triggered' is non-empty.

  • scan_watchlistFree

    Scan a watchlist and report which names did something actionable. For each ticker: last close, day change, gap, distance from the 20/50/200-day averages and the 52-week high, ATR%, and volume vs its 20-day average -- plus which rules fired (near_52w_high, volume_spike, crossed_above/below_200dma, at_20dma, gapped_over_1atr). Sorted most-actionable first. The Sunday-evening tool: run it over your list, then feed interesting names into build_trade_plan.

Public scan report

scanner v0.1.9 · 2026-09-23 · same rubric, same numbers if you re-run it

1 high
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 388ms20/20
  • Tool poisoning25 tool descriptions checked15/15
  • Auth qualityopen endpoint exposes 8 write-action tools with no auth3/15
  • Maintenancelast push 37 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (1)

  • highWrite-action tools reachable without authenticationauth.open-write
Overall 77/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the Quant Brain repository's README, as published. We do not edit it. Read it on GitHub

🧠 Quant Brain MCP

Turn Claude into a quantitative analyst for US and Indian equities.

Ask in plain English. Get sized trade plans, portfolio optimization, backtests, and price alerts — grounded in real market data, not vibes.

You:    "Scan my watchlist and build a trade plan for whatever looks most actionable.
         ₹2,00,000 equity, 1% risk."

Claude: RELIANCE.NS flagged (at 20-DMA, volume 1.8x average).

        TRADE PLAN — RELIANCE.NS (long)
        Entry           ₹1,310.00
        Stop            ₹1,270.10   (swing low, 2.1 ATR)
        Size            50 shares   (₹65,500 — 32.8% of equity)
        Max loss        ₹1,995      (1.0% of equity)
        Targets         1R ₹1,349.90 · 2R ₹1,389.80 · 3R ₹1,429.70
        Invalidation    Thesis invalid below ₹1,270.10 — exit without debate.

No API keys. No accounts. Connect one URL and start asking.

⚡ Quickstart

Claude Desktop / Claude Web → Settings → Connectors → Add custom connector → Streamable HTTP:

https://mcp-quant-brain.onrender.com/mcp

That's the whole setup. Try: "What's RELIANCE trading at, and is it overbought?"

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.

🛠 What you get — 25 tools

Full reference with every parameter: docs/tools.md

🔄 The workflow it's built around

flowchart LR
    S["🔍 <b>scan_watchlist</b><br/>what moved this week?"] --> N["📰 <b>get_news</b><br/>why did it move?"]
    N --> P["📐 <b>build_trade_plan</b><br/>entry · stop · size · targets"]
    P --> A["🔔 <b>price_alert</b><br/>watch my levels"]
    A -.->|level breaks → notified| P
    subgraph deeper["go deeper anytime"]
        I["📊 indicators"] ~~~ B["🧪 backtests"] ~~~ O["💼 optimizer"]
    end
    S -.-> deeper

🔔 Price alerts that survive restarts

You:  "Alert me if RELIANCE drops below ₹1,270"        → stored server-side (Postgres)
      ...
Bot:  "PRICE ALERT FIRED — RELIANCE.NS moved below 1270.00, now at 1268.20"

Alerts 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.

🎯 Why this instead of a stock screener?

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

claude mcp add --transport http quant-brain-mcp https://mcp-quant-brain.onrender.com/mcp
Add to Cursor

Quant Brain: common questions

Is Quant Brain MCP server safe?
Mostly: it is graded B (77/100). Read the Quant Brain safety report
How do I install Quant Brain?
It runs remotely at mcp-quant-brain.onrender.com. Add it to Claude Code, Claude Desktop or Cursor with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Quant Brain need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Quant Brain maintained?
The last commit was 38 days ago (2026-08-16). The latest release is v1.0.0.
Is Quant Brain up?
100% of our last 16 checks got an answer. We check remote servers about four times a day.
What can I use instead of Quant Brain?
Servers from other publishers that do the same job: HPSILab Quant Finance MCP server, Tradingview MCP server and AlgoVault — Crypto Quant Trade Calls MCP server. Compare all Quant Brain alternatives.

Alternatives to Quant Brain

Same job from other publishers: the closest match first, then the best rated.

All Quant Brain alternatives →
  • HPSILab Quant Finance
    HPSILab Quant finance MCP for US stocks, ETFs, options, Monte Carlo, backtesting, and risk analysis.
    A
  • Tradingview
    Real-time market data, screeners, technical analysis & backtesting for stocks, crypto and forex.
    A
  • AlgoVault — Crypto Quant Trade Calls
    The Brain Layer for AI Trading Agents — quant calls + cross-venue arb across perp venues via MCP.
    A
  • Quant Research
    Crypto backtest statistics: the server owns the trial count, so it cannot be understated.
    A
  • Stoxly
    Free stock, ETF & crypto analysis: 10-point score, verdict and key metrics for any ticker.
    A
Quant Brain vs HPSILab Quant FinanceQuant Brain vs TradingviewQuant Brain vs AlgoVault — Crypto Quant Trade Calls

More from paarths-collab →