Protect Google ADK agents with Dome content Guards or the full Trust Runtime.
TL;DR: For content protection, wrap Dome as ADK model callbacks with generate_adk_input_callback and generate_adk_output_callback. For full Agent security (identity, tool permissions, audit), pass your ADK Agent to secure_agent().
Google ADK Agents expose before_model_callback and after_model_callback hooks that run immediately before and after the model is invoked. Dome plugs into both. You have two levels of protection.
Add Dome input and output Guardrails as ADK callbacks. Install the ADK dependency first (pip install google-adk).
from google.adk.agents import Agentfrom vijil_dome import Domefrom vijil_dome.integrations.adk import ( generate_adk_input_callback, generate_adk_output_callback,)# Dome is async-first, but ADK does not yet support async model callbacks.# nest_asyncio bridges the two until ADK adds async callback support.import nest_asyncionest_asyncio.apply()dome = Dome()guard_input = generate_adk_input_callback(dome)guard_output = generate_adk_output_callback(dome)my_agent = Agent( model="gemini-2.0-flash-001", name="my_agent", description="An agent built with Google ADK, protected by Dome", instruction="You are a friendly, question-answering AI agent.", before_model_callback=guard_input, after_model_callback=guard_output,)
Both factories accept optional blocked_message (a custom message returned when content is blocked) and additional_callback (another callback to chain after Dome):
guard_input = generate_adk_input_callback( dome, blocked_message="Your request was blocked by a Guardrail.", additional_callback=my_logging_callback,)
For identity attestation, tool-permission enforcement, and audit on top of content Guards, wrap the Agent with secure_agent(). It detects ADK automatically and injects input, output, and tool callbacks in place.
from google.adk.agents import Agentfrom vijil_dome import secure_agentagent = Agent( model="gemini-2.0-flash-001", name="travel_agent", instruction="You help users book travel.", tools=[search_flights, process_payment],)# Injects input/output Guards plus tool-permission checks (MAC).secure_agent(agent, agent_id="travel-agent", mode="enforce")
The Trust Runtime adapter requires the trust-adapters extra (which includes google-adk):
pip install "vijil-dome[trust,trust-adapters]"
In enforce mode, a denied tool call is short-circuited before the tool runs. In warn mode, the violation is logged but execution continues. See Trust Runtime for identity and manifest details.
To deploy an ADK Agent protected with Dome, follow ADK’s Cloud Run deployment guide via the gcloud CLI and add vijil-dome to your Agent’s requirements.txt. Use a container large enough for Dome’s models: we recommend --cpu=4 --memory=8Gi.
Deploying directly via the ADK CLI is not supported, because it does not let you set requirements or increase the container image size. The default 1 CPU / 512 MB container is insufficient for Dome’s default configuration. Use 4 CPUs and 8 GiB memory.
Dome uses the annoy package (the embeddings extra) for a fast embeddings store. annoy is not currently compatible with Google ADK on Cloud Run. Use the default in-memory option if you need embeddings-based Detectors. Most default configurations do not require it.
For a full walkthrough of guarding and deploying a multi-agent ADK setup, see the Vijil blog post.
