.well-known location.
Retrieve an agent card
Every agent exposes its card at:A2A-Version: 1.0 header indicating the protocol version the server uses.
Card structure
Capabilities
Thecapabilities object advertises what the agent can do:
streaming: Whether the agent supports streaming responses via SSE. Iftrue, you can usemessage:streamandtasks:subscribe.pushNotifications: Whether the agent can push task updates to a client-supplied webhook.
pushNotifications is future scope. The tasks/pushNotificationConfig/* management endpoints are not yet implemented. Expect this field to be false until they ship.Supported interfaces
Each entry insupportedInterfaces declares one A2A protocol binding:
Both bindings share the same base URL (
/v2/agentic/agents/{agentId}/a2a). The JSONRPC binding sends a JSON-RPC envelope; the HTTP+JSON binding uses path-suffixed endpoints like message:send and message:stream. See A2A protocol for details.
Skills
Each skill in theskills array represents a capability the agent exposes through its connectors. The id is a bare UUID (the connector’s external ID). Skills help clients understand what an agent can do before sending a message.
Using cards for discovery
Agent cards enable a discovery workflow:- A client fetches the card from a known agent URL.
- The client inspects
supportedInterfacesto determine which protocol binding to use. - The client checks
capabilities.streamingto decide whether to use blocking or streaming calls. - The client reviews
skillsto understand what the agent can do. - The client sends a message using the appropriate binding.
Retrieving an agent card requires the same authentication as any other v2 API request. You need a valid bearer token and tenant header.
Card example
The following is a typical agent card for a coding agent:Next steps
- Learn about connectors, which power the skills advertised in the card
- Read the A2A protocol page for details on the two protocol bindings
- Follow the quickstart to create an agent and retrieve its card