MCP.so
登录

QuantToGo MCP Server

@michaeljiangmingfeng-debug

基本信息

分类

金融与商务

许可证

MIT

传输方式

stdio

作者

michaeljiangmingfeng-debug

提交者

michaeljiangmingfeng-debug

关于 QuantToGo MCP Server

Macro-factor quantitative signal source for AI agents via MCP. 宏观因子量化信号源。

QuantToGo MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

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

QuantToGo MCP Server 工具

8

List all available trading strategies with live performance data. Returns strategy name, market (US/China), total return, drawdown, and recent returns.

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).

Get custom market indices — China A-share momentum and strategy-weighted momentum. Requires API key (get one free via register_trial).

Compare multiple strategies side-by-side — returns, drawdown, and recent performance.

Get subscription plans and free trial info.

Start a free 30-day trial. Provide your email, get an API key instantly. Calling again with the same email returns your existing account.

Get today's buy/sell signals for a strategy. Requires API key from register_trial.

Check subscription status and remaining trial days. Requires API key from register_trial.

概览

What is QuantToGo MCP Server?

QuantToGo MCP Server is a macro-factor quantitative signal source accessible via the Model Context Protocol (MCP). It provides 8 tools and 1 resource for AI agents to discover live trading signals, self-register for a free trial, and check subscription status. All performance data is forward-tracked from live signals, not backtested.

How to use QuantToGo MCP Server?

Install by adding a configuration entry to your MCP client (e.g., Claude Desktop, Cursor, or Coze). Use npx -y quanttogo-mcp for local stdio transport, or connect via remote SSE or Streamable HTTP endpoints. Then ask your AI assistant to list strategies, register a trial, or query signals.

Key features of QuantToGo MCP Server

  • 8 tools for discovery, registration, and signal retrieval
  • 1 resource: quanttogo://strategies/overview
  • Zero configuration – works out of the box
  • Self-registration for 30-day free trial with email
  • All signal performance is forward-tracked and immutable
  • AI-native – callable directly by any MCP-compatible agent

Use cases of QuantToGo MCP Server

  • An AI assistant lists all strategies and compares their live performance
  • A user registers for a free trial and receives an API key instantly
  • An agent queries the latest buy/sell signals for a specific strategy
  • Compare up to 8 strategies side-by-side within a conversation

常见问题

1

What does QuantToGo provide vs. a trading platform or asset manager?

QuantToGo is a quantitative signal source, not a trading platform, asset manager, or copy-trading community. It publishes systematic trading signals based on macroeconomic factors; users decide whether to act on them in their own brokerage accounts.

2

What are the runtime/dependency requirements?

The server is an npm package (`quanttogo-mcp`) and requires Node.js to run via `npx`. No additional configuration is needed.

3

Where do the signals and performance data live?

All signals are timestamped at the moment of publication and stored immutably. The git history of the repository provides an independent audit trail. Live performance data is hosted on QuantToGo servers and accessed via the MCP tools.

4

What transports and authentication are supported?

Transports: local stdio, remote SSE (`https://mcp.quanttogo.com/sse`), and Streamable HTTP (`https://mcp-us.quanttogo.com:8443/mcp`). Authentication: free tools require no API key; signal tools require an API key obtained via `register_trial` with an email address.

5

Are there any known limits?

The README does not mention explicit limits, but the free trial is 30 days, and subscription info is available via `get_subscription_info`.

评论

金融与商务 分类下的更多 MCP 服务器