A React shell that renders A2UI surfaces streamed from the Restaurant Finder Agent over the Agent-to-Agent (A2A) protocol.
- Node.js
- uv
- Python — see
requires-pythonin the agent's pyproject.toml
From the repository root, install dependencies and build all packages:
yarn install
yarn build:allIn one terminal, start the
Restaurant Finder Agent on its default
port (10002):
cd samples/agent/adk/restaurant_finder
cp .env.example .env # then edit .env and set GEMINI_API_KEY (do not commit .env)
uv run .In another terminal, start the React dev server:
cd samples/client/react/shell
yarn devVite serves the app on http://localhost:5003 and proxies /a2a requests to the
agent running on localhost:10002.
Open http://localhost:5003 in your browser (or follow the link printed in the console).
Important: The sample code provided is for demonstration purposes and illustrates the mechanics of A2UI and the Agent-to-Agent (A2A) protocol. When building production applications, it is critical to treat any agent operating outside of your direct control as a potentially untrusted entity.
All operational data received from an external agent—including its AgentCard, messages, artifacts, and task statuses—should be handled as untrusted input. For example, a malicious agent could provide crafted data in its fields (e.g., name, skills.description) that, if used without sanitization to construct prompts for a Large Language Model (LLM), could expose your application to prompt injection attacks.
Similarly, any UI definition or data stream received must be treated as untrusted. Malicious agents could attempt to spoof legitimate interfaces to deceive users (phishing), inject malicious scripts via property values (XSS), or generate excessive layout complexity to degrade client performance (DoS). If your application supports optional embedded content (such as iframes or web views), additional care must be taken to prevent exposure to malicious external sites.
Developer Responsibility: Failure to properly validate data and strictly sandbox rendered content can introduce severe vulnerabilities. Developers are responsible for implementing appropriate security measures—such as input sanitization, Content Security Policies (CSP), strict isolation for optional embedded content, and secure credential handling—to protect their systems and users.