MCP

Use the hosted RobotRock MCP server to add human-in-the-loop approvals to any MCP-native agent runtime.

Endpoint: https://mcp.robotrock.io/mcp

Tools

Authentication (per customer)

Every customer uses their own API key from the RobotRock dashboard (Settings → API Keys). The hosted server validates the key and routes tasks to that customer's tenant.

{
  "mcpServers": {
    "robotrock": {
      "url": "https://mcp.robotrock.io/mcp",
      "headers": {
        "X-Api-Key": "ll_your_api_key"
      }
    }
  }
}

You can also pass Authorization: Bearer ll_your_api_key.

There is no shared server API key — each customer's key identifies their workspace.

Waiting for a human response

SSE push (recommended)

When connected over HTTP MCP:

1. Call send_to_human → receive { taskId, delivery: "sse" }
2. Keep the MCP SSE connection open
3. When a human handles the task, the server pushes a notification:

{
  "type": "robotrock/task_handled",
  "taskId": "task_abc",
  "action": { "id": "approve", "title": "Approve", "data": {} },
  "handledBy": "alice@acme.com",
  "handledAt": "2026-06-07T12:00:00.000Z"
}

Polling fallback

Call get_task with the taskId until status is handled. Use this if the SSE connection dropped or your MCP client does not handle server notifications.

Self-hosting (monorepo)

Deploy apps/mcp to Vercel. Required environment variables:

Routes:

• GET/POST/DELETE /mcp — MCP Streamable HTTP
• POST /webhooks/robotrock — RobotRock task handled webhooks
• GET /health — health check

When to use MCP vs other integrations

Related

• Send to human
• Webhooks