Reverse engineer anything with agents, from app behavior down to native binaries.
MCP Metatrader5 Server
A Model Context Protocol (MCP) server for interacting with the MetaTrader 5 trading platform. This server provides AI assistants with tools and resources to access market data,…
Install
git clone https://github.com/Qoyyuum/mcp-metatrader5-serverInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →MetaTrader 5 MCP Server
A Model Context Protocol (MCP) server for MetaTrader 5, allowing AI assistants to interact with the MetaTrader 5 platform for trading and market data analysis. Documentation
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/Qoyyuum/mcp-metatrader5-server.git
cd mcp-metatrader5-server
uv sync
uv run mt5mcp
Requirements
- uv (recommended) or pip
- Python 3.11 or higher
- MetaTrader 5 terminal installed on Windows
- MetaTrader 5 account (demo or real)
Usage
Quick Start
The server runs in stdio mode by default for MCP clients like Claude Desktop:
uv run mt5mcp
Development Mode (HTTP)
For testing with HTTP transport, create a .env file:
MT5_MCP_TRANSPORT=http
MT5_MCP_HOST=127.0.0.1
MT5_MCP_PORT=8000
Then run:
uv run mt5mcp
The server will start at http://127.0.0.1:8000
Installing for MCP Clients
Method 1: Using uvx (Simplest - No Installation Required) ⭐
Add this configuration to your MCP client's config file:
For Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"mcp-metatrader5-server": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/Qoyyuum/mcp-metatrader5-server",
"mt5mcp"
]
}
}
}
Method 2: Using FastMCP Install (Recommended)
git clone https://github.com/Qoyyuum/mcp-metatrader5-server
cd mcp-metatrader5-server
After git cloning the repo, run the following commands:
For MCP JSON format
uv run fastmcp install mcp-json src/mcp_mt5/main.py
For Claude Desktop
uv run fastmcp install claude-desktop src/mcp_mt5/main.py
For Claude Code
uv run fastmcp install claude-code src/mcp_mt5/main.py
For Cursor
uv run fastmcp install cursor src/mcp_mt5/main.py
For Gemini CLI
uv run fastmcp install gemini-cli src/mcp_mt5/main.py
Method 3: Manual Configuration
Add this to your claude_desktop_config.json or whatever LLM config file:
{
"mcpServers": {
"mcp-metatrader5-server": {
"command": "uvx",
"args": [
"--from",
"mcp-metatrader5-server",
"mt5mcp"
]
}
}
}
API Reference
Connection Management
initialize(): Initialize the MT5 terminallogin(account, password, server): Log in to a trading accountshutdown(): Close the connection to the MT5 terminal
Market Data Functions
Similar plugs
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype…
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)