QuantContext

zomma-dev/quantcontext-mcp-server

Wraps Yahoo Finance historical data and Fama-French factors into three deterministic tools: screen_stocks filters S&P 500, Nasdaq 100, or Russell 2000 by fundamentals, momentum, or technical signals; backtest_strategy runs a rebalance loop over history with stop-loss support and returns CAGR, Sharpe, drawdown, and trade logs; factor_analysis decomposes returns into market, size, value, and momentum exposures with alpha t-stats. Everything caches locally after first run, so screening takes under a second and backtests finish in 3-8 seconds. No API keys, no config file. Useful when you want Claude to run quantitative strategy research with real numbers instead of hallucinating performance metrics.

GitHub stars: 8
tools: 3
transport: STDIO
last updated: Mar 8, 2026

View on GitHub

Tools

3 tools

Public tool metadata for what this MCP can expose to an agent.

screen_stocksFilter S&P 500, Nasdaq 100, or Russell 2000 by fundamentals, momentum, quality, technical signals, or a multi-factor blend. Returns ranked candidates.

Filter S&P 500, Nasdaq 100, or Russell 2000 by fundamentals, momentum, quality, technical signals, or a multi-factor blend. Returns ranked candidates.

No parameter schema in public metadata yet.

backtest_strategyTest a strategy over history with a rebalance-loop engine. Returns CAGR, Sharpe, max drawdown, equity curve, and trade log.

Test a strategy over history with a rebalance-loop engine. Returns CAGR, Sharpe, max drawdown, equity curve, and trade log.

No parameter schema in public metadata yet.

factor_analysisDecompose strategy returns into Fama-French factors (market, size, value, momentum). Returns alpha with t-statistic, factor loadings, and R-squared.

Decompose strategy returns into Fama-French factors (market, size, value, momentum). Returns alpha with t-statistic, factor loadings, and R-squared.

No parameter schema in public metadata yet.

Readme

QuantContext

QuantContext is an MCP server that turns plain-English strategy descriptions into executable quant research: screen stocks by any criteria, backtest over historical data, and run factor analysis to see where the returns come from. Every number is computed from real market data, not generated by an LLM. Results are fully reproducible.

Works with Claude, Codex, OpenCode, or any other MCP-compatible coding agent.

Install

pip install quantcontext-mcp

Claude Code:

claude mcp add quantcontext -- quantcontext

Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "quantcontext": {
      "command": "quantcontext"
    }
  }
}

No API keys. No configuration.

Tools

Three tools that compose into a full research workflow:

screen_stocks -> backtest_strategy -> factor_analysis

View the full README on GitHub

Details

Repository: github.com/zomma-dev/quantcontext-mcp-server
Website: quantcontext.ai
Category: Finance & Commerce
Package: quantcontext-mcp
Transport: STDIO
Registry: MCP registry, active

Related Finance & Commerce MCP servers

View all

HasData DuckDuckGohasdata/duckduckgo-mcpDuckDuckGo search as JSON. Ranked results, ads in their own array, 37 regions.7stars

SODAX Builders MCPgosodax/builders-sodax-mcp-serverCross-network DeFi API data, AMM analytics, and SDK docs for 17+ networks.0stars

MINDtheastraway/mind-mcp-serverMIND knowledge-graph memory for agents. 44 tools: CRM, Life, MoneyMIND, Budget, Sheets, Email, Sign.7stars

Canli Capitalarhancanli/canlicapital443 finance tools, 60 prompts: quant, SEC and EU filings, fact checks, rates, odds, DeFi, macro.6stars

JustOneAPIjustoneapi-official/justoneapi-mcpDiscover social and commerce APIs without login; authenticate for API calls and account data.6stars

Agent Centralagentcentral-to/agent-central-mcpHosted Amazon Seller Central and Amazon Ads MCP server for Claude, ChatGPT, Cursor, and agents.6stars