IRL Gateway runs on your own machine — the client starts it, so there is no endpoint to ping. 2 093 installs a week from pypi. Last commit 8 Oct 2026.
An AI agent's trading mandate it can't break: checked before every order, reasoning sealed in IRL.
Today is the operative word: we check IRL Gateway every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add irl-gateway -- uvx irl-gateway
{
"mcpServers": {
"irl-gateway": {
"args": [
"irl-gateway"
],
"command": "uvx"
}
}
}
[mcp_servers.irl-gateway]
command = "uvx"
args = ["irl-gateway"]
{
"mcpServers": {
"irl-gateway": {
"args": [
"irl-gateway"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"irl-gateway": {
"args": [
"irl-gateway"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
IRL_BASE_URL (Your IRL server, e.g. https://irl.example.com), IRL_API_TOKEN (Bearer token for the IRL server), IRL_AGENT_ID (The agent registered on IRL (its mandate)), IRL_MODEL_HASH (The model hash the agent was registered with (64 hex)), GATEWAY_BROKER (paper (default, live prices, no keys) or exchange), PAPER_BALANCES (Starting paper balances, e.g. USDT=1000).
The author declared them in the registry entry; get the values from the project itself.
Read-only checks for proposed orders against evidence and policy; no trading or payment authority.
Trading Card Value Checker: the site's own MCP server — dataset; every answer cites the site.
Pre-send risk check for AI agents that move money — screen an address or payment URL before sending.
Let an AI agent read and trade a MetaTrader 5 account over MCP, behind a human-approval gate.
Check stablecoin and x402 payments before an AI agent pays: approve, hold or reject.
Trading MCP server for AI agents, with live market data, account reads and controlled execution.
Verify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.
Agent-native service discovery and purchase-intent routing to Stripe-hosted checkout.
Answers built from our own checks of this server.