1. Conduid
  2. Developer Tools
  3. Quant MCP
MCP server · Developer Tools

Quant MCP

by · github.com/irohan0/quant-mcp

Model Context Protocol server giving AI agents typed, read-only access to market data, indicators, backtests and position sizing. Bounded responses for the context budget, model-recoverable errors, execution assumptions returned with every backtest.

Unclaimed ai-agentsbacktestingllm-toolsmcpmodel-context-protocolquantitative-financetypescript
InstallView source
34Low

Scored 17 days ago · breakdown

About Quant MCP

Quant MCP is an MCP server published by irohan0 in the Developer Tools category: model Context Protocol server giving AI agents typed, read-only access to market data, indicators, backtests and position sizing. Bounded responses for the context budget, model-recoverable errors, execution assumptions returned with every backtest.

The repository has 2 stars and 0 forks, with the last commit 4 months ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/irohan0/quant-mcp

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Tools (14)

backtestVectorised SMA / RSI / Momentum / MACD vs buy-and-hold

Parameters not published.

composite_score**One 0–100 score + Strong-Buy→Strong-Sell verdict** blending all lenses

Parameters not published.

factors**Fama-French 3-factor + momentum** regression (betas, alpha, R², contributions)

Parameters not published.

fundamentalsRatios + **two-stage DCF / reverse-DCF** + **Piotroski F-Score** + **Altman Z-Score**

Parameters not published.

macro_overlayFRED macro indicators (rates, CPI YoY, VIX, yield curve) + rolling correlation

Parameters not published.

market_regime**Gaussian HMM** regime classification + transition matrix + posteriors

Parameters not published.

monte_carlo**Regime-aware** / GBM / bootstrap forward simulation, fan chart, hit-probability, projected VaR

Parameters not published.

options_analyticsIV skew, put/call ratio, max pain, IV term structure, in-house **Black-Scholes greeks**

Parameters not published.

pairsEngle-Granger + ADF cointegration, hedge ratio, half-life, z-score backtest

Parameters not published.

portfolio_optimisationMax-Sharpe, Min-Vol, Risk-Parity + efficient frontier + correlation heatmap

Parameters not published.

Show all 14 tools
price_historyOHLCV fetch with candlestick + Bollinger + volume chart

Parameters not published.

risk_metricsSharpe, Sortino, Calmar, VaR, CVaR, beta, Jensen's alpha, skew, kurtosis

Parameters not published.

sentimentMulti-source news headline sentiment (VADER over yfinance + Yahoo/Google RSS)

Parameters not published.

technicalsRSI, MACD, Bollinger, ADX, Stochastic, ATR, OBV, S/R, patterns → composite signal

Parameters not published.

Ask AI

✦

Ask AI about Quant MCP

Powered by Claude · Grounded in docs

I know everything about Quant MCP. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About Quant MCP

How do I install Quant MCP?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Quant MCP safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Quant MCP still maintained?

Yes — the last commit was 4 months ago. The repository has 2 stars and 0 forks.