TradeOS AI

TradeOS를 GPT, Claude 및 기타 MCP 호환 AI 도구에 연결하세요. TradeOS MCP 서버를 통해 어시스턴트가 거래 데이터, 지표, 전략 로직 및 에이전트 워크플로우와 직접 작업하여 TradeOS 환경에서 시장 분석, 설정 모니터링 및 거래 인텔리전스 자동화를 지원합니다.

gitbook.io에서 보기

문서

For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to page URLs; this page is available as Markdown.

TradeOS MCP Integration & Usage

By integrating MCP (Model Context Protocol), you can connect TradeOS’s professional-grade trading tools directly to your AI workflow, enabling real-time market data access, technical analysis, and enhanced trading insights.

Quick Start

Select the MCP entry point or trigger an MCP-related action to begin the connection process.

Method 1: Homepage

Method 2: Homepage → Side Menu → MCP

Connection & Login Guide

  1. Initiate an MCP connection request.
  1. A browser window will open for authentication. Sign in using one of the following methods: Google、Facebook、Email Login
  2. Once authentication is complete, TradeOS AI is successfully connected. Then, You can use TradeOS AI within your workflow.

Authorization & Permissions

During use, the AI may request access to TradeOS technical analysis features. Please click “Allow” to continue.

Note: The AI requires your explicit authorization to access TradeOS's underlying data and analysis tools in order to provide accurate and professional market insights.

Advanced Configuration

Endpoint Configuration

If you are an advanced user, developer, or need to manually configure the connection within your custom Agent or local client (e.g., Claude Desktop), please use the following address:

  • Endpoint URL: https://ai.tradeos.xyz/api/agent/mcp/mcp-call

Example

Example 1: Claude-NVDA vs QQQ Spread Trend Analysis

Prompt: 1yo help me analyze NVDA/QQQ (put this as ticker) spread in terms of trend / momentum / volatility

Example 2: Cursor-Relative Strength Ranking Against SPY

Prompt: help me analyze LLY, GOOG, AMZN, META, MSFT, GLD, QQQ against SPY via spread analysis (ticker like LLY / SPY, GOOG / SPY ...), then rank them in scores 0~100 where 0 is strong short position and 100 is strong long position

Example 3: ChatGPT - analyze NVDA/SPY

Prompt: Help me analyze NVDA/SPY