A Python-based MCP server that allows AI LLMs to execute trades on the MetaTrader 5 platform.
This is a Model Context Protocol (MCP) server built with Python to enable AI LLMs to trade using MetaTrader platform.
Financial trading involves significant risk, and the developers of this package disclaim any liability for any losses or profits; this package is provided solely to facilitate MetaTrader 5 trade executions via AI LLMs using the Model Context Protocol (MCP). By using this package, you assume all risks and agree not to hold the developers liable or to initiate any legal action for any damages, losses, or profits.
Make sure you have Python version 3.10+ and MetaTrader 5 terminal installed in your workspace. Then install the package:
pip install metatrader-mcp-server
Then you need to enable algorithmic trading on MetaTrader 5 terminal. Open Tools > Options
and check Allow algorithmic trading
.
To use this package to enable trading operations via Claude Desktop app, please add this into your Claude Desktop configuration:
{
"mcpServers": {
"metatrader": {
"command": "metatrader-mcp-server",
"args": [
"--login", "<YOUR_MT5_LOGIN>",
"--password", "<YOUR_MT5_PASSWORD>",
"--server", "<YOUR_MT5_SERVER>"
]
}
}
}
You can use this MCP server with other LLMs such as OpenAI's GPT by using its HTTP server and Open WebUI.
To start, make sure you have installed the package. Then, run the server:
metatrader-http-server --login <YOUR_MT5_LOGIN> --password <YOUR_MT5_PASSWORD> --server <YOUR_MT5_SERVER> --host 0.0.0.0 --port 8000
It will launch HTTP server locally on port 8000 and automatically launch MetaTrader 5 terminal.
On Open WebUI settings page, navigate to Tools menu. Then click plus button on "Manage Tool Servers". Add http://localhost:8000
(or whatever you set your port is).
If all is well, you can now access the tools via chat using available models, such as gpt-4o
or o4-mini
.
For full version checklist, see version-checklist.md.
Task | Status | Done | Tested |
---|---|---|---|
Connect to MetaTrader 5 terminal | Finished | ✅ | ✅ |
Develop MetaTrader client module | Finished | ✅ | ✅ |
Develop MCP Server module | Finished | ✅ | ✅ |
Implement MCP tools | Finished | ✅ | ✅ |
Publish to PyPi | Finished | ✅ | ✅ |
Claude Desktop integration | Finished | ✅ | ✅ |
OpenAPI server | Finished | ✅ | ✅ |
Open WebUI integration | Finished | ✅ | ✅ |
Google ADK integration | On progress | - | - |
For developers, see Developer's Documentation.
Programmatic control over Windows system operations including mouse, keyboard, window management, and screen capture using nut.js.
Tools to the query and execute of Dify workflows
Automate your local browser
Interact with your Obsidian vault using natural language.
Connects AI agents to the Feishu/Lark platform for automating tasks like document processing, conversation management, and calendar scheduling.
A Jira integration that allows LLMs to act as project managers and personal assistants for teams.
MCP server for easy access to education data through your Canvas LMS instance.
Interact with the accounting data in your business using our official MCP server
Perform queries and entity operations in your Fibery workspace.
A server for managing gatherings and sharing expenses.