Retrieve a run's sandbox status
/api/v1/runs/{run_id}/sandboxRetrieve limited lifecycle metadata for the sandbox attached to a run. The response never exposes a provider sandbox identifier, environment variables, network configuration, a desktop URL, or a terminal token.
available reports whether control may currently be acquired. Acquire control before submitting work, and use the returned control ID for subsequent operations.
Required access
Credentials: automation account, delegated token, user API key
User API keys use the owner’s current permissions, subject to any key restrictions. Capability scopes below apply to automation account keys and delegated tokens.
Scope: runs:read
Programmatic credentials only. The ordinary run visibility rule applies, but an open control is returned only to the exact credential that owns it. Browser sessions and agent principals cannot use this surface.
A user-owned key prefixed gsmc_uk_, bound to one organization. It follows its owner's current membership, role and resource permissions, optionally restricted to read-only access. No X-Org-Id header is needed; a conflicting organization is rejected. Credential creation, personal connection setup and human attestations require a signed-in session. Runs are private to the calling user; sharing an agent grants access to your own personal memory of it, never to the agent's own memory.
In: header
Path Parameters
Header Parameters
Selects the active organization for a direct user session that has more than one membership. Automation account keys and delegated tokens are each bound to one organization and ignore it.
Response Body
application/json
application/json
application/json
application/json
application/json
application/json
application/json
curl -X GET "https://example.com/api/v1/runs/0/sandbox" \ -H "Authorization: Bearer $GUEST_MACHINES_API_KEY"{ "run_id": 0, "available": true, "lifecycle_state": "string", "control": { "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08", "run_id": 0, "phase": "active", "release_requested": true, "requested_at": "2019-08-24T14:15:22Z", "started_at": "2019-08-24T14:15:22Z", "last_interaction_at": "2019-08-24T14:15:22Z", "ended_at": "2019-08-24T14:15:22Z" }}List a run's MCP results GET
List local and provider-hosted MCP call receipts for one run in ascending settlement order. This is the explicit result handoff for an app that started a run; ordinary run events and conversation entries continue to omit MCP result content.
Acquire programmatic control of a run's sandbox POST
Request temporary programmatic control of the sandbox already owned by this run. Acquisition is asynchronous: poll the returned control until it is active before submitting operations.