mcpField
M
MTContext

MTContext

Remote
github.com/mtcontextFinance0Updated 13w ago
Repository

About MTContext

MTContext is a cloud-hosted remote MCP server connecting MetaTrader 4/5 terminals to AI clients. It is aimed at traders who want market and account data, indicator analysis, and trade actions, which default to dry runs.

Key features

  1. 01Read live prices and account state
  2. 02Inspect open positions
  3. 03Run indicators such as RSI and MACD
  4. 04Calculate position size
  5. 05Default trade calls to dry run

Use cases

  1. 01Check EURUSD bid and ask prices
  2. 02Review account balance and open positions
  3. 03Analyze indicators for a symbol and timeframe
  4. 04Preview the effect of a proposed trade

MCP support

Each account has a remote Streamable HTTP MCP endpoint that connects clients to a MetaTrader terminal. Trade-affecting calls default to dry_run until explicitly confirmed.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.mtcontext.com/mcp/v1
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://mcp.mtcontext.com/mcp/v1Auth required

Tools

Details

From the project README

MTContext MCP Quickstart

Connect Claude, Cursor, or any MCP-compatible client to a MetaTrader 4 or 5 terminal — no Python, no local server to run.

MTContext is a cloud-hosted, remote MCP server. There's nothing to clone, build, or pip install from this repo — this repo exists to document the connection and point at the real thing. (This is intentional: the server implementation itself is closed-source, cloud infrastructure, not something you run yourself.)

How it works

  1. Sign up (free tier: read-only market data, no card required).
  2. Drag one Expert Advisor file (.ex5 for MT5, .ex4 for MT4 — MT4 support coming soon) onto a chart in your MetaTrader terminal.
  3. Copy your ready-made MCP config snippet from the dashboard and paste it into your client's config.
  4. Ask your AI client, in plain English, for live prices, account state, indicators, or — when you explicitly allow it — trades. Every trade-affecting call defaults to dry_run: true until you confirm.

Connection

MTContext exposes a single remote Streamable HTTP MCP endpoint per account:

{
  "mcpServers": {
    "mtcontext": {
      "type": "http",
      "url": "https://mcp.mtcontext.com/mcp/v1",
      "headers": {
        "Authorization": "Bearer YOUR_LICENSE_KEY"
      }
    }
  }
}

Get your real YOUR_LICENSE_KEY from your dashboard after connecting a terminal — see examples/claude_desktop_config.example.json.

What you can ask it

  • "What's the current EURUSD bid and ask?"
  • "What's my account balance and open positions?"
  • "Run RSI and MACD on GBPUSD, H1."
  • "Size a position on XAUUSD risking 1% of my equity with a 30-pip stop."
  • "Place a dry-run buy on EURUSD, 0.1 lots, and show me what would happen."

Full tool reference: docs.mtcontext.com. Setup guides and troubleshooting: help.mtcontext.com.

Why not a self-hosted MCP server?

Several open-source MetaTrader MCP servers exist and require installing Python and running a local process yourself, usually MT5-only, with no safety layer beyond what you build. MTContext trades that developer-only setup for a one-file install, MT4 and MT5, and a dry-run-by-default safety model — aimed at traders, not just developers who happen to trade.

Links

License

The contents of this repository (documentation and examples) are MIT licensed — see LICENSE. This does not cover the MTContext service itself, which is proprietary.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.