Files
adk-python/contributing/samples/api_registry_agent/README.md
T
Kathy WuandCopybara-Service ec4ccd718f feat: Create APIRegistryToolset to add tools from Cloud API registry to agent
This calls the cloudapiregistry.googleapis.com API to get MCP tools from the project's registry, and adds them to ADK.

Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 837166909
2025-11-26 10:01:58 -08:00

22 lines
848 B
Markdown

# BigQuery API Registry Agent
This agent demonstrates how to use `ApiRegistry` to discover and interact with Google Cloud services like BigQuery via tools exposed by an MCP server registered in an API Registry.
## Prerequisites
- A Google Cloud project with the API Registry API enabled.
- An MCP server exposing BigQuery tools registered in API Registry.
## Configuration & Running
1. **Configure:** Edit `agent.py` and replace `your-google-cloud-project-id` and `your-mcp-server-name` with your Google Cloud Project ID and the name of your registered MCP server.
2. **Run in CLI:**
```bash
adk run contributing/samples/api_registry_agent -- --log-level DEBUG
```
3. **Run in Web UI:**
```bash
adk web contributing/samples/
```
Navigate to `http://127.0.0.1:8080` and select the `api_registry_agent` agent.