Google Vertex AI agent

Google Vertex AI agent for Spatial9: 8 free, MIT licensed files that connect agents and data platforms to the Spatial9 spatial audio MCP server and A2A agent.

Spatial9 on Google Cloud and Vertex AI

Two ways to use Spatial9 on Google Cloud: an agent your team talks to, or a scheduled job with no agent.

File · What it does

spatial9_agent/agent.py · ADK agent with Spatial9 tools through McpToolset, key from Secret Manager

deploy_agent_engine.py · Deploys that agent to Vertex AI Agent Engine

batch_job.py · Cloud Run job: BigQuery queue in, Cloud Storage files out, 3 workers

cloud_run_job.sh · Secret, job and Cloud Scheduler setup

Notes

• Use tool_filter to give each agent only the tools it needs.
• ADK can also expose an agent over A2A. Spatial9 has its own A2A endpoint at https://spatial9.ai/a2a if you prefer agent-to-agent tasks over tool calls.
• The Agent Engine SDK changes often. Pin versions and check the current Google docs before deploying.

Files

• solutions/vertex-ai/batch_job.py
• solutions/vertex-ai/cloud_run_job.sh
• solutions/vertex-ai/deploy_agent_engine.py
• solutions/vertex-ai/Procfile
• solutions/vertex-ai/README.md
• solutions/vertex-ai/requirements.txt
• solutions/vertex-ai/spatial9_agent/__init__.py
• solutions/vertex-ai/spatial9_agent/agent.py

Download every file as a zip · View on GitHub