Mobilerun · Schema
Agent
An Agent of the owner: its lifecycle state, profile and runtime.
Mobile AutomationCloud PhonesAI AgentsDevice FleetTestingResidential IP
Properties
| Name | Type | Description |
|---|---|---|
| id | string | |
| status | string | `pending`: created but not provisioned yet, it takes no turns. `active`: ready for turns. `failed`: provisioning gave up (see `errorCode`); the Agent is archived. `archived`: read-only. `disabled`: sw |
| threadSessionId | stringnull | Active chat on the active machine, pinned first, then session lastActiveAt DESC, id DESC. Null for pending/archived Agents or no thread. |
| welcomePending | boolean | Whether this active primary Agent is still due its one-time greeting: the welcome-back for an adopted primary, or the onboarding greeting for a primary whose chat never had a message. |
| threadPreview | objectnull | Newest thread excerpt (90 characters), awaits-input and timestamp, from at most 20 newest rows. Null when the thread has no rows. |
| primary | boolean | Whether this is the owner's primary Agent, the one a chat session uses when it names no `agentId`. |
| profile | object | |
| createdAt | string | |
| provisionedAt | stringnull | When provisioning of the Agent completed (ISO 8601); null while a newly created Agent is still pending and after its provisioning failed. |
| archivedAt | stringnull | |
| disabledReason | stringnull | Why a `disabled` Agent is disabled: `owner` chose it, `over-limit` the plan grants fewer Agent slots than the owner had enabled. Null while the Agent is not disabled. |
| errorCode | stringnull | Why provisioning failed, null otherwise. An open set: new codes can appear. Codes written today: `provision_timeout`, `agent_limit_reached`, `provision_failed`; a code the harness reports for a failed |
| runtime | stringnull | Whether the Agent is running right now, derived from stored state only. `waking`: an active start, its machine is provisioning or a restart/rehydrate is pending and changed within the last 10 minutes |
| lastActiveAt | stringnull | Latest activity of the Agent (newest chat session activity or live turn heartbeat), ISO 8601; null when it has never been active. |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/mobilerun-ai/json-schema/mobilerun-ai-agent-schema.json",
"title": "Agent",
"description": "An Agent of the owner: its lifecycle state, profile and runtime.",
"x-generated": "2026-11-18",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/mobilerun-ai-openapi.json#/components/schemas/Agent",
"type": "object",
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"status": {
"type": "string",
"enum": [
"active",
"pending",
"failed",
"archived",
"disabled"
],
"description": "`pending`: created but not provisioned yet, it takes no turns. `active`: ready for turns. `failed`: provisioning gave up (see `errorCode`); the Agent is archived. `archived`: read-only. `disabled`: switched off by the owner or because the plan grants fewer Agent slots; it takes no turns and holds no slot, and the owner can enable it again while a slot is free."
},
"threadSessionId": {
"type": [
"string",
"null"
],
"format": "uuid",
"description": "Active chat on the active machine, pinned first, then session lastActiveAt DESC, id DESC. Null for pending/archived Agents or no thread."
},
"welcomePending": {
"type": "boolean",
"description": "Whether this active primary Agent is still due its one-time greeting: the welcome-back for an adopted primary, or the onboarding greeting for a primary whose chat never had a message."
},
"threadPreview": {
"type": [
"object",
"null"
],
"properties": {
"excerpt": {
"type": [
"string",
"null"
]
},
"awaitsInput": {
"type": "boolean"
},
"timestamp": {
"type": [
"string",
"null"
],
"format": "date-time"
}
},
"required": [
"excerpt",
"awaitsInput",
"timestamp"
],
"description": "Newest thread excerpt (90 characters), awaits-input and timestamp, from at most 20 newest rows. Null when the thread has no rows."
},
"primary": {
"type": "boolean",
"description": "Whether this is the owner's primary Agent, the one a chat session uses when it names no `agentId`."
},
"profile": {
"$ref": "#/$defs/AgentProfile"
},
"createdAt": {
"type": "string"
},
"provisionedAt": {
"type": [
"string",
"null"
],
"description": "When provisioning of the Agent completed (ISO 8601); null while a newly created Agent is still pending and after its provisioning failed."
},
"archivedAt": {
"type": [
"string",
"null"
]
},
"disabledReason": {
"type": [
"string",
"null"
],
"enum": [
"owner",
"over-limit",
null
],
"description": "Why a `disabled` Agent is disabled: `owner` chose it, `over-limit` the plan grants fewer Agent slots than the owner had enabled. Null while the Agent is not disabled."
},
"errorCode": {
"type": [
"string",
"null"
],
"description": "Why provisioning failed, null otherwise. An open set: new codes can appear. Codes written today: `provision_timeout`, `agent_limit_reached`, `provision_failed`; a code the harness reports for a failed start is passed through."
},
"runtime": {
"type": [
"string",
"null"
],
"enum": [
"awake",
"sleeping",
"waking",
null
],
"description": "Whether the Agent is running right now, derived from stored state only. `waking`: an active start, its machine is provisioning or a restart/rehydrate is pending and changed within the last 10 minutes (a timed-out or stalled start reads `sleeping`). `awake`: the machine is running and this Agent has been started in the current run. `sleeping`: everything else (stopped or parked machine, an Agent the running harness has not started yet, or an Agent that is not active). `awake` can lag a machine stop until the reconciler converges."
},
"lastActiveAt": {
"type": [
"string",
"null"
],
"description": "Latest activity of the Agent (newest chat session activity or live turn heartbeat), ISO 8601; null when it has never been active."
}
},
"required": [
"id",
"status",
"threadSessionId",
"welcomePending",
"threadPreview",
"primary",
"profile",
"createdAt",
"provisionedAt",
"archivedAt",
"disabledReason",
"errorCode"
],
"$defs": {
"AgentAvatarConfig": {
"type": "object",
"properties": {
"seed": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"maxLength": 128
},
{
"type": "integer",
"minimum": 0,
"maximum": 4294967295
}
]
},
"color": {
"type": "string",
"enum": [
"slate",
"red",
"orange",
"amber",
"lime",
"green",
"teal",
"cyan",
"blue",
"indigo",
"violet",
"pink"
]
}
},
"additionalProperties": false,
"description": "Configuration of a `blob` avatar: its seed and optional user-chosen palette color. A color-only config retains the default seed fallback."
},
"AgentPersona": {
"type": "object",
"properties": {
"displayName": {
"type": [
"string",
"null"
]
},
"avatarKind": {
"type": [
"string",
"null"
],
"enum": [
"blob"
]
},
"avatarConfig": {
"anyOf": [
{
"$ref": "#/$defs/AgentAvatarConfig"
},
{
"type": "null"
}
]
}
},
"required": [
"displayName",
"avatarKind",
"avatarConfig"
]
},
"AgentProfile": {
"allOf": [
{
"$ref": "#/$defs/AgentPersona"
},
{
"type": "object",
"properties": {
"instructions": {
"type": [
"string",
"null"
]
},
"modelProfile": {
"type": [
"string",
"null"
]
}
},
"required": [
"instructions",
"modelProfile"
]
}
],
"description": "Persona of the Agent plus its individual instructions passage; `instructions` is null when none is set."
}
}
}
Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/mobilerun-ai-agent"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.