MetaTrader 5 MCP Bridge

MetaTrader 5 MCP Bridge

Let an AI agent manage your MetaTrader 5 account over [Model Context Protocol](https://modelcontextprotocol.io) - with configurable human approval gate.

A Hermes agent placing then closing a real 0.01-lot trade on a demo account, end-to-end over MCP on Linux.

Not a mock-up - the same round-trip in MetaTrader 5's own History tab; the tickets and balance match the recording.

⚠️ **This software places _real_ trades through your MetaTrader 5 terminal with

real orders and irreversible fills.** Read

DISCLAIMER.md

and SECURITY.md

before connecting it to a live account. Always test using your demo account first.

Runs locally - in the same process tree as your agent, no cloud, no telemetry. Windows (native) or Linux (via Docker); Python 3.10+.

📖 The story behind this: this project is built step by step in

*Wiring AI agent into MetaTrader 5*,

Part 1 of the *Trade with AI agent* series on the Fintrix engineering blog.

What it is

mt5-mcp lets an AI agent read your MetaTrader 5 account and place trades through it, over the Model Context Protocol.

• 12 read-only tools: account, quotes, positions, orders, history, OHLC bars, broker-authoritative margin estimates, and native chart screenshots (Windows). No consent gate.
• 4 mutating tools: place_order, modify_order, cancel_order, close_position, each behind a preflight + human-consent + idempotency + audit layer.
• 3 subscribable resources: live account://, positions://, and quotes://{symbol} snapshots that push change notifications.
• 2 ready-to-use Claude Code skills ship in .claude/skills/: mt5-market-data and mt5-trading teach an agent how to read the account and run the consent flow safely.

Full catalogue and the consent flow: [docs/tools.md](https://github.com/vincentwongso/mt5-trading-mcp/blob/main/docs/tools.md).

Why mt5-mcp

• A safety layer, not just an API wrapper. Every mutating call routes through preflight checks -> an opt-in human-consent gate (arm it to require approval) -> idempotency -> an append-only audit log, so you can put a human in the loop on trades and always keep a replayable record of what the agent did.
• An honest threat model. It treats an LLM wired to place_order as a live attack surface and says so plainly - the MCP is explicitly *not* the security boundary (see SECURITY.md).
• Verifiable proof, not a mock-up. The demo above is a real round-trip; the tickets and balance match MetaTrader 5's own History tab.
• Local-first. No cloud, no telemetry; runs beside your agent. Windows-native or Linux via an all-in-one Docker image (no rpyc version-matching).

Quickstart (Windows, native)

pip install mt5-trading-mcp

1. Launch MetaTrader 5 and log into your broker. Enable AlgoTrading (toolbar button green).
2. Verify the terminal is reachable: python -m mt5_mcp doctor: expect [INFO] backend: native and [PASS] lines.
3. Run it: python -m mt5_mcp serve.

Wire it to OpenClaw in one command (registers the mcp.servers entry):

openclaw mcp set mt5-mcp '{"command":"python","args":["-m","mt5_mcp","serve"]}'

Quickstart (Linux, Docker)

The MT5 terminal + the MCP run headless in an all-in-one image; your agent talks MCP over HTTP. No host Python, no bridge.

cp deploy/.env.example deploy/.env   # add MT5_LOGIN / MT5_PASSWORD / MT5_SERVER

docker compose -f deploy/docker-compose.yml up -d

Log the terminal in once via the KasmVNC web UI at http://127.0.0.1:3001 (File -> Login to Trade Account; persists across restarts), then point your agent at http://127.0.0.1:8765/mcp. Wire it to OpenClaw in one command:

openclaw mcp set mt5-mcp '{"url":"http://127.0.0.1:8765/mcp","transport":"streamable-http"}'

Full walkthrough: [docs/installation.md](https://github.com/vincentwongso/mt5-trading-mcp/blob/main/docs/installation.md).

Chart screenshots (Windows only)

get_chart_screenshot(symbol, timeframe, annotations?) returns a PNG of the native MT5 chart, optionally annotated, so an LLM can read it visually (candles, support/resistance, patterns). Because the MetaTrader5 Python API cannot capture charts, this uses a small MQL5 Expert Advisor that runs inside a GUI terminal and calls ChartScreenShot().

See Chart annotations for marking up support/resistance lines, trendlines and notes before capture.

Setup (one time):

1. Install and attach the AgentScreenshot EA - see mql5/README.md.
2. Optionally set a template so your indicators/drawings appear in the shot: [screenshot] template = "agent.tpl" in your config, or leave it unset for the default chart.

Config knobs ([screenshot] section): width (default 1600), height (default 900), template (default none), timeout_s (default 10).

Not available on the headless Linux/Docker deployment: it needs a GUI terminal. Off Windows the tool returns SCREENSHOT_NOT_SUPPORTED.

For AI agents

If you've been handed this repository to install and run, follow the runbook in [docs/agents.md](https://github.com/vincentwongso/mt5-trading-mcp/blob/main/docs/agents.md). It covers platform detection, install, verification, registering the server, and the hard safety rules for trades - read it before calling any mutating tool.

Documentation

Safety

mt5-mcp is not the security boundary, the broker's MT5 server enforces the hard limits (margin, max-lot, symbol permissions). Pre-flight checks in the policy engine are UX guardrails to catch agent mistakes early, not security controls.

The human-consent gate is opt-in and off by default: auto_approve_notional defaults to 0, so mutating calls auto-execute (full-open) - intended for trusted or unattended agents. Arm the gate by setting `auto_approve_notional` > 0: orders/closes whose notional is at or above it then return an ApprovalPreview you must confirm, and modifying a stop to widen or remove it also requires approval. The pre-flight limits (max_*) and symbol allow/deny lists are likewise opt-in (0 / empty = off). Every mutating call is recorded in an append-only audit JSONL log regardless. For vulnerability disclosure, see SECURITY.md.

Architecture

mt5-mcp wraps the MetaTrader 5 Python library behind a FastMCP server. A single MT5Client (src/mt5_mcp/adapter/) owns the terminal connection, broker-timezone inference, and type conversions; everything else sits on top of it. The Pydantic models in src/mt5_mcp/types.py / src/mt5_mcp/config.py are the source of truth for the data and config schemas.

     Agent / MCP client  (Hermes, OpenClaw, Claude Code, Claude Desktop, …)

│ │ stdio · loopback HTTP ▼ ┌──────────────────────────────────────────────────────────┐ │ FastMCP server │ │ │ │ tools/ resources/ policy/ │ │ read + subscribable consent · idempotency │ │ mutating account/quotes · audit (JSONL) │ │ │ │ streaming/ - change-detection poller + dispatcher │ │ types.py · config.py - Pydantic schemas: source of │ │ truth for data + config │ │ │ └──────────────────────────────────────────────────────────┘ │ ▼ ┌──────────────────────────────────────────────────────────┐ │ │ │ adapter/ MT5Client │ │ one terminal connection · broker-TZ inference · │ │ type conversions · transparent reinit │ │ │ └──────────────────────────────────────────────────────────┘ │ ▼ MetaTrader 5 Python library -> broker terminal -> broker server

The module paths shown (tools/, resources/, policy/, streaming/, adapter/, types.py, config.py) all live under src/mt5_mcp/.

Contributing

Contributions are welcome, see CONTRIBUTING.md for the dev setup, test workflow, and project principles.

L