Skip to content

Grok HumanLeg.ai humanleg_get_task

How to: Grok HumanLeg.ai humanleg_get_task

client:Grok transport:streamable-http tool:humanleg_get_task

Add HumanLeg.ai to Grok

  1. 01

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

{
  "mcpServers": {
    "humanleg": {
      "type": "http",
      "url": "https://humanleg.ai/mcp"
    }
  }
}
  1. 02

    Save the file and restart Grok.

  2. 03

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

  3. 04

    If nothing happens, check the server is running and that HumanLeg.ai'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

HumanLeg.ai will not start until these are set, so humanleg_get_task never becomes available.

  • HUMANLEG_API_URL
  • HUMANLEG_AGENT_TOKEN

Same tool, other clients

This list was read from the server itself, by connecting to it and calling tools/list on 10 November 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.