quanttogo-mcp
Summary: This server exposes trading-strategy performance, signal, market-index, and subscription/API-key tools—different from the reason-index/risk tools described in the README.
List available US/China trading strategies with live returns, drawdown, and recent performance.
Get detailed strategy performance: returns, drawdown, Sharpe, win rate, and daily NAV history for charting.
Retrieve custom China A-share momentum and strategy-weighted momentum index data.
Compare multiple strategies side by side (2–8 product IDs).
Get today’s buy/sell signals for a strategy (up to 50).
Register for a free 30-day trial via email and instantly receive an API key.
View subscription plans and free-trial info.
Check subscription status and remaining trial days.
Most data tools require an API key obtained from
register_trial.
Supports integration with Coze (扣子) platform via remote SSE transport, enabling AI agents to access quantitative trading signals and strategy data through the MCP protocol.
Utilizes GitHub for hosting and version control of performance data, with forward-tracked signals timestamped and immutable in git commit history for independent audit trail.
Uses GitHub Actions for automated weekly updates of strategy performance data, ensuring the performance table in the README is automatically refreshed with latest metrics.
Distributes the MCP server as an npm package, allowing installation via npx command for easy setup and deployment across different environments.
References Chinese-language technical articles on Zhihu (知乎) that explain the quantitative signal source paradigm and QTGS evaluation framework for the Chinese-speaking audience.
QuantToGo MCP — Macro-Factor Quantitative Signal Source
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
Strategy | Market | Factor | Total Return | Max Drawdown | Sharpe | Frequency |
Dip-Buying Beacon (US) | US | Sentiment: VIX panic reversal | +671.8% | -60.0% | 1.5 | Daily |
CNH-CHAU | US | FX: CNH-CSI300 correlation | +659.6% | -43.5% | 2.0 | Weekly |
Smoothed 3x Nasdaq | US | Trend: TQQQ timing | +558.3% | -69.9% | 1.4 | Monthly |
Large/Small Cap IF-IC Rotation | China | Liquidity: large/small cap rotation | +446.2% | -22.0% | 1.9 | Daily |
Smart Money CSI300 Timing | China | FX: CNY-index correlation | +385.8% | -29.9% | 1.8 | Daily |
PCR Retail Contrarian | US | Sentiment: Put/Call Ratio | +247.9% | -24.8% | 1.7 | Daily |
Unpopular Stock Contrarian | China | Attention: low-volume value | +227.6% | -32.0% | 1.5 | Monthly |
Dip-Buying Beacon (A-Share) | China | Sentiment: limit-down rebound | +81.8% | -9.1% | 1.6 | Daily |
Last updated: 2026-05-04 · Auto-updated weekly via GitHub Actions · Verify in git history
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.
Related MCP server: Stock SDK MCP Server
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:
Dimension | Key Question |
Forward Tracking Integrity | Are all signals timestamped and immutable, including losses? |
Strategy Transparency | Can you explain in one sentence what the strategy profits from? |
Custody Risk | Are user funds always under user control? Zero custody = zero run-away risk. |
Factor Robustness | Is the alpha source a durable economic phenomenon, or data-mined coincidence? |
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 / Remote SSE
{
"mcpServers": {
"quanttogo": {
"url": "https://mcp.quanttogo.com/sse",
"transportType": "sse"
}
}
}Remote Streamable HTTP
https://mcp-us.quanttogo.com:8443/mcpTools
Discovery (free, no auth)
Tool | Description | Parameters |
| List all strategies with live performance | none |
| Detailed data + daily NAV history for one strategy |
|
| Side-by-side comparison of 2-8 strategies |
|
| QuantToGo custom indices (DA-MOMENTUM, QTG-MOMENTUM) |
|
| Subscription plans + how to start a free trial | none |
Signals (requires API Key — get one via register_trial)
Tool | Description | Parameters |
| Register a 30-day free trial with email, get API Key instantly |
|
| Get latest buy/sell signals for a strategy |
|
| Check trial status and remaining days |
|
Resource: quanttogo://strategies/overview — JSON overview of all strategies.
Try It Now
Ask your AI assistant:
"List all QuantToGo strategies and compare the top performers."
"I want to try QuantToGo signals. Register me with my-email@example.com."
"Show me the latest trading signals for the US panic dip-buying strategy."
"Help me register for a QuantToGo trial with email xxx@gmail.com, then show me the latest signals for US stock strategies."
🔗 Links
Audience | URL |
Visitors / Free Trial | |
Subscribers / Invited Users | |
AI Agents / Mechanism Audit |
中文
什么是 QuantToGo?
QuantToGo 是一个宏观因子量化信号源——不是交易平台,不是资管产品,不是跟单社区。
我们运行基于宏观经济因子(汇率周期、流动性轮动、恐慌情绪、跨市场联动)的量化策略模型,持续发布交易信号。用户接收信号后,自主判断、自主执行、自主承担盈亏。我们不触碰用户的任何资金。
类比:天气预报告诉你明天大概率下雨,但不替你决定带不带伞。
核心特征
宏观因子驱动:每个策略的信号来源都有明确的经济学逻辑,不是数据挖掘
指数为主:80%以上标的为指数ETF/期货,规避个股风险
前置验证:所有信号从发出那一刻起不可篡改,完整展示回撤和亏损
零资金委托:你的钱始终在你自己的券商账户
AI原生:通过MCP协议可被任何AI助手直接调用
快速体验
对你的AI助手说:
"帮我列出QuantToGo所有的量化策略,看看它们的表现。"
"帮我注册 QuantToGo 试用,邮箱 xxx@gmail.com,然后看看最新的交易信号。"
"有没有做A股的策略?最大回撤在30%以内的。"
🔗 链接
用户类型 | 地址 |
访客 / 免费试用 | |
订阅用户 | |
AI 代理 / 机制审计 |
相关阅读
《量化信号源》系列文章:
宏观因子量化:为什么"硬逻辑"比"多因子"更适合信号源模式
当AI学会调用量化策略:MCP协议与量化信号源的技术实现
用AI助手获取实盘量化信号:一份实操指南
License
MIT
Available Tools
8 toolscheck_subscriptionB
Check subscription status and remaining trial days. Requires API key from register_trial.
Inputs: apiKey (required).
compare_strategiesA
Compare multiple strategies side-by-side — returns, drawdown, and recent performance.
Inputs: productIds (required).
get_index_dataC
Get custom market indices — China A-share momentum and strategy-weighted momentum. Requires API key (get one free via register_trial).
Inputs: apiKey (required), indexId.
get_signalsA
Get today's buy/sell signals for a strategy. Requires API key from register_trial.
Inputs: apiKey (required), productId (required), limit.
get_strategy_performanceA
Get detailed performance for a specific strategy — returns, drawdown, Sharpe, win rate, and daily NAV history for charting. Requires API key (get one free via register_trial).
Inputs: apiKey (required), productId (required), includeChart.
get_subscription_infoC
Get subscription plans and free trial info.
Inputs: no named parameters.
list_strategiesA
List all available trading strategies with live performance data. Returns strategy name, market (US/China), total return, drawdown, and recent returns.
Inputs: no named parameters.
register_trialA
Start a free 30-day trial. Provide your email, get an API key instantly. Calling again with the same email returns your existing account.
Inputs: email (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool has a clearly distinct purpose: subscription management, strategy listing, performance, signals, indices, comparison, and trial registration. No overlapping functionality.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., check_subscription, get_strategy_performance, list_strategies). The verbs vary appropriately for different actions.
8 tools is well-scoped for a financial strategy platform covering subscription, strategy data, signals, indices, and comparisons. Each tool earns its place.
The tool set covers the core workflow: trial registration, subscription status, strategy listing, performance details, signals, indices, and comparison. No obvious gaps for the stated purpose.
Maintenance
Related MCP Connectors
Live macro data for AI agents: regime, conditions, liquidity, with input provenance. No signup.
Macroeconomic and market data for AI agents: rates, credit, volatility, calendars and screeners.
China A-share data for AI agents: 57 read-only tools plus 6 tools for your own watchlist.
Macroeconomic and FX time-series data for AI agents: indicators, calendars, COT, forex, commodities.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to perform quantitative research and backtesting for China A-shares and futures, including data fetching, backtesting, factor analysis, and experiment tracking through MCP tools.2Apache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to query real-time and historical market data across A-share, Hong Kong, US, and fund markets, including quotes, K-line data, technical indicators, sector and futures/options data. It also supports batch market scans, composite stock analysis, condition-based screening, and built-in analyst prompts and skills for financial workflows.153 npmISC
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and HTTP clients to access standardized financial market data, technical indicators, fundamentals, news, money-flow, and filings across A-shares, US equities, ETFs, indices, and crypto, with MCP tools and CSV/JSON exports for code workflows.-
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to access real-time and historical quotes, K-lines, technical indicators, sector, futures, and options data, plus composite stock analysis, market screening, and monitoring workflows across A-shares, Hong Kong, and US markets. It also provides built-in prompts and skills for financial analysis tasks.153 npmISC