agent_authorize

macOS

Purpose

Decides whether this computer's installed Agent Mesh contract allows acting on one Mesh message, from the message's sender and type only, never its content. For an allowed action it returns a cap_id and the exact steps: pass mesh_cap_id with each step's tool call, in order; any other call is refused while the action is in progress. For an informational message it says how to close it (ack or reply). A rejection says why and nothing may be done for that message. Works only when Mesh auto-wake is enabled on this computer.

Required inputs

• agent_id — Your agent_id, the same one you used in agent_checkin.
• message_id — The id of the message from agent_inbox.

Permissions and confirmation

Explicit confirmation parameter: inspect the schema and tool description before any real call. The documentation example keeps confirm false. Obtain user authorization before performing the action.

• Use only the apps, accounts and resources authorized by the user on this platform. Consult this tool's platform-specific description for its connection and permission requirements; this catalog does not assert additional OAuth scopes or OS entitlements.

{
  "properties": {
    "agent_id": {
      "description": "Your agent_id, the same one you used in agent_checkin.",
      "type": "string"
    },
    "confirm": {
      "description": "Must be true to act. Without it the call returns a preview and changes nothing.",
      "type": "boolean"
    },
    "message_id": {
      "description": "The id of the message from agent_inbox.",
      "type": "integer"
    }
  },
  "required": [
    "agent_id",
    "message_id"
  ],
  "type": "object"
}

Documentation example

Do not execute this example. These concrete inputs refer to a fictional demonstration dataset. Resolve real handles and obtain user authorization before any real call.

{
  "agent_id": "demo-reviewer",
  "confirm": false,
  "message_id": 101
}