Get Agent
Retrieve an agent in a simplified view: its attached skills as one flat list, plus core configuration.
SimplifiedAIAgent), not the full object that Create Agent returns. Instead of the low-level graph, attached_tools, oas, and fully-resolved skill schemas, the agent’s attached skills are surfaced as one flat tools array (see the AgentTool shape below). Use Add Agent Tool and Remove Agent Tool to change them. Fields such as skills, gated_commands, secret_bindings, can_self_schedule and default_user_id are not part of this view; they come back on the full object that Create Agent and Update Agent return.
Path Parameters
Response
instructions)xpi:workflow:dusk, or an emoji)manager, regular, a2a, curl or orchestrationDRAFT, ACTIVE (deployed) or INACTIVEanthropic)claude-sonnet-5)external-harness (a coding CLI chosen by harness_settings.default_cli) or agno (the built-in loop)serverless or containerexternal-harness agent; null for agno.sdk, webhook, slack)AgentTool:null when unavailable; null-check before reading).Authorizations
API Key for authentication
Path Parameters
Response
Successful Response
Lean agent view exposing tools as one simple list, hiding low-level graph/oas internals.
Agent name.
Agent id.
Agent description.
Agent icon.
Agent type.
manager, regular, a2a, curl, orchestration Agent status.
DRAFT, ACTIVE, INACTIVE LLM provider.
LLM model.
Runtime: agno (built-in) or external-harness (Claude Code / Codex / OpenCode).
serverless or container.
serverless, container External harness settings (default CLI, per-CLI models, permission mode, per-turn resources ceilings); absent for built-in agents.
Agent instructions.
Attached knowledge base ids.
Trigger source types (sdk, webhook, slack, ...).
Tools attached to this agent.
Creation timestamp.
Creator user id.
Creator details.

