Skip to content

Grok EthersFlow — Trust Gate for AI Agents verify_agent_action

How to: Grok EthersFlow — Trust Gate for AI Agents verify_agent_action

client:Grok transport:streamable-http tool:verify_agent_action

Add EthersFlow — Trust Gate for AI Agents to Grok

  1. 01

    Open .mcp.json (in your project root) and merge this in. Keep any servers already there.

{
  "mcpServers": {
    "ethersflow": {
      "type": "http",
      "url": "https://www.ethersflow.com/api/mcp"
    }
  }
}
  1. 02

    Save the file and restart Grok.

  2. 03

    Ask for something verify_agent_action does. Grok lists the server's tools on connect and calls verify_agent_action itself — you do not invoke it by name.

  3. 04

    If nothing happens, check the server is running and that EthersFlow — Trust Gate for AI Agents's identifier in your config matches the one above exactly.

Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs

Set these first

EthersFlow — Trust Gate for AI Agents will not start until these are set, so verify_agent_action never becomes available.

  • ETHERSFLOW_TOKEN

Same tool, other clients

This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what the server actually exposes, not what its listing claims.

Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.