Use automatic registration

Agent Registry can discover and register agents hosted on supported Google Cloud runtimes without requiring you to manually call the Agent Registry API. Depending on the runtime, this registration process happens automatically or requires an opt-in configuration step during deployment.

This document explains how to enable discovery for agents on supported runtimes. If you host an agent externally or on an unsupported runtime, see Use manual registration.

The metadata and skills extracted from an agent during its registration depends on the agent's protocol. For more information, see Register agents.

Register agents from Vertex AI Agent Engine

If you develop agents with Vertex AI Agent Engine and deploy them using the Vertex AI SDK, registration in Agent Registry is automatic.

The Agent2Agent (A2A) protocol is an open standard that lets agents declare their capabilities and identity. The following example shows how to deploy an agent implementing the A2A protocol to Vertex AI Agent Engine. For more information, see Deploy an agent.

# Create and deploy the agent
# This action automatically registers the agent in Agent Registry
remote_agent = client.agent_engines.create(
    agent=my_a2a_agent, # Your defined A2A object
    config={
        "display_name": "my-support-agent",
        "description": "An agent that handles support tickets.",
        "requirements": ["google-cloud-aiplatform[agent_engines,langchain]"],
    },
)

As you update or delete your agent in Vertex AI Agent Engine, Agent Registry automatically synchronizes those changes.

Register built-in Google agents

Built-in Google agents, such as Google Workspace and Gemini Enterprise agents, are automatically integrated with Agent Registry. You don't need to perform any configuration or deployment steps. These agents are ingested and available for discovery within your registry.

Register agents from GKE

You can register agents deployed on Google Kubernetes Engine by adding the apphub.cloud.google.com/functional-type: "AGENT" annotation to your deployments. This annotation identifies the deployment as an AI agent, letting Agent Registry perform an introspection scan.

The following example shows a GKE agent deployment manifest. For more information, see Deploy and orchestrate AI agents.

apiVersion: apps/v1
kind: Deployment
metadata:
  name: my-agent
  annotations:
    # Identifies the workload as an AI agent
    apphub.cloud.google.com/functional-type: "AGENT"
spec:
  selector:
    matchLabels:
      app: my-agent
  template:
    metadata:
      labels:
        app: my-agent
    spec:
      containers:
      - name: server
        image: gcr.io/my-project/my-agent:1.0.0

When the deployment is applied, the GKE cluster automatically attempts to fetch metadata from the agent and syncs it directly into the Agent Registry data model.

Verify registration

You can verify that Agent Registry successfully registered your agents by listing them:

Console

  1. In the Google Cloud console, go to Agent Registry:

    Go to Agent Registry

  2. From the project picker, select the Google Cloud project where you set up Agent Registry.

  3. Select the Agents tab.

    The page displays a list of all registered agents and their details, such as name, identifier, description, runtime, and location.

  4. Filter the list by the agent's location or their runtime resource:

    • To filter by location, click the Location menu, select the locations you want to filter, and click Apply.
    • To filter by runtime, click the Runtime menu, select the runtimes you want to filter, and click Apply.

    The page displays a filtered list of the registered agents for your selected conditions.

gcloud

If you have multiple agents, or if you want to confirm the registration of a specific agent, such as an automatically registered agent, you can filter the list by the agent's metadata.

To do this, make sure you have set up your Google Cloud CLI environment for Agent Registry, and then run:

gcloud alpha agent-registry agents list \
  --project=PROJECT_ID \
  --location=REGION \
  --filter="FILTER_EXPRESSION"

Replace the following:

  • PROJECT_ID: The project ID.
  • REGION: The registry region.
  • FILTER_EXPRESSION: The filter expression for the agents that you want to filter. For example, to filter by display name, you can use displayName='DISPLAY_NAME'. To filter by the globally unique identifier (URN), you can use agentId='urn:agent:AGENT_URN'.

Built-in Google services use a URN format that depends on where the agent is deployed. For example, you can discover built-in Google Workspace agents by filtering your list for the googleapis.com publisher using --filter="agentId:'urn:agent:googleapis.com:*'"