MetaTrader 5 MCP Server
Enables ChatGPT Desktop to interact with MetaTrader 5 for trading, market data access, and trade management via HTTP/ngrok.
README
MetaTrader 5 MCP Server for ChatGPT Desktop
A Model Context Protocol (MCP) server for MetaTrader 5, specifically adapted for ChatGPT Desktop integration. This fork enables ChatGPT to interact with the MetaTrader 5 platform for trading and market data analysis via HTTP transport and ngrok tunneling.
Based on: mcp-metatrader5-server by Abdul Qoyyuum Focus: ChatGPT Desktop integration with HTTP/ngrok support
Features
- Connect to MetaTrader 5 terminal
- Access market data (symbols, rates, ticks)
- Place and manage trades
- Analyze trading history
- Integrate with AI assistants through the Model Context Protocol
Installation
From PyPI
uvx --from mcp-metatrader5-server mt5mcp
From Source
git clone https://github.com/jorgearturoyap-debug/metatrader-5-for-Chatgpt-Desktop.git
cd metatrader-5-for-Chatgpt-Desktop
uv sync
uv run mt5mcp
Requirements
- ChatGPT Plus subscription or higher (Free tier doesn't support MCP)
- ChatGPT Desktop application (latest version)
- ngrok for tunneling: https://ngrok.com/download
- uv package manager (recommended) or pip
- Python 3.11 or higher
- MetaTrader 5 terminal installed on Windows
- MetaTrader 5 account (demo or real)
Quick Start for ChatGPT Desktop
See CHATGPT_SETUP.md for detailed step-by-step setup instructions.
TL;DR:
- Clone this repo and install dependencies:
uv sync - Configure your MT5 credentials in
.envfile - Run
start_chatgpt.batto start the server with ngrok - Copy the ngrok HTTPS URL
- Add the connector in ChatGPT Desktop settings
- Start trading with ChatGPT!
What's Different from the Original?
This fork includes:
- ✅ HTTP transport support for ChatGPT Desktop (via ngrok)
- ✅ Automated startup script (
start_chatgpt.bat) that handles server + ngrok - ✅ ChatGPT-specific documentation and setup guides
- ✅ Pre-configured for HTTP mode in
fastmcp.json - ✅ Spanish language support in setup guides
Credits & Acknowledgments
Original Author
This project is based on the excellent work by Abdul Qoyyuum (Qoyyuum) in the original mcp-metatrader5-server repository. All core MT5 functionality and MCP implementation credit goes to the original author.
Contributors
Special thanks to all contributors who have helped improve this project in the private development repository before its public release.
Development Tools
Important Note: This adaptation was created entirely using AI-assisted development tools. The maintainer (jorgearturoyap-debug) is not a professional programmer. All code, documentation, and improvements were developed with the assistance of:
- Claude Code CLI - AI-powered coding assistant by Anthropic
- GitHub Codex CLI - AI-powered code completion and generation
This project demonstrates how AI tools can empower non-programmers to adapt and customize complex software for specific use cases (ChatGPT Desktop integration in this case).
License
This project inherits the license from the original mcp-metatrader5-server repository. Please see the original repository for license details.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。