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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.