QuantToGo 说法百科 MCP server

QuantToGo MCP — 宏观因子量化信号源

English | 中文

A macro-factor quantitative signal source accessible via MCP (Model Context Protocol). 8 tools, 1 resource, zero config. AI Agents can self-register for a free trial, query live trading signals, and check subscription status — all within the conversation. All performance is forward-tracked from live signals — not backtested.

QuantToGo is not a trading platform, not an asset manager, not a copy-trading community. It is a quantitative signal source — like a weather forecast for financial markets. We publish systematic trading signals based on macroeconomic factors; you decide whether to act on them, in your own brokerage account.

📊 Live Strategy Performance

<!-- PERFORMANCETABLESTART -->

Last updated: 2026-09-21 · Auto-updated weekly via GitHub Actions · Verify in git history

<!-- PERFORMANCETABLEEND -->

All returns are cumulative since inception. Forward-tracked daily — every signal is timestamped at the moment it's published, immutable, including all losses and drawdowns. Git commit history provides an independent audit trail.

What is a Quantitative Signal Source?

Most quantitative services fall into three categories: self-build platforms (high technical barrier), asset management (you hand over your money), or copy-trading communities (unverifiable, opaque). A signal source is the fourth paradigm:

• A quant team runs strategy models and publishes trading signals
• You receive the signals and decide independently whether to act
• You execute in your own brokerage account — we never touch your funds
• All historical signals are forward-tracked with timestamps — fully auditable

Think of it as a weather forecast: it tells you there's an 80% chance of rain tomorrow. Whether you bring an umbrella is your decision.

How to evaluate any signal source — the QTGS Framework:

Quick Start

Claude Desktop / Claude Code

{
  "mcpServers": {
    "quanttogo": {
      "command": "npx",
      "args": ["-y", "quanttogo-mcp"]
    }
  }
}

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "quanttogo": {
      "command": "npx",
      "args": ["-y", "quanttogo-mcp"]
    }
  }
}

Coze（扣子）/ Remote SSE

Shortened. The full README is on GitHub.