Spatial9 enterprise recipes: Databricks, Snowflake, Vertex AI and Bedrock

Free, commented code to run governed Spatial9 spatial audio renders from Databricks, Snowflake, Google Vertex AI and Amazon Bedrock. Microsoft Fabric is not supported.

Spatial9 for enterprise platforms

Governed catalog renders from the data and AI platforms enterprises already run. Every recipe follows the same rules: key in the platform's secret store, at most 3 renders at once, an idempotency_key per track and version, and results written back for audit.

Platform · Folder · Pattern

Databricks · databricks · Unity Catalog connection, Lakeflow Job, Volumes, optional AI Gateway MCP Services

Databricks Solutions Accelerator · databricks/solution-accelerator · Asset Bundle with Auto Loader, MCP, A2A and REST API routes, audit table and gold views

Snowflake · snowflake · External access integration, Python procedure, Task, Cortex Agent custom tool

Google Cloud and Vertex AI · vertex-ai · ADK agent with McpToolset, Agent Engine, Cloud Run job and Scheduler, BigQuery

AWS and Amazon Bedrock · bedrock · Strands agent, Lambda, Step Functions, S3, AgentCore Gateway

Any Python runtime · shared/spatial9_mcp.py · The MCP handshake with requests only

Any Python runtime · shared/spatial9_a2a.py · Agent2Agent tasks: send, follow, cancel, webhooks

Other orchestrators such as Prefect, Dagster, Salesforce Agentforce, ServiceNow and IBM watsonx Orchestrate can reuse shared/spatial9_mcp.py or connect to https://spatial9.ai/mcp as a remote MCP server where they support one.

Microsoft Fabric is not supported.

Guide: https://spatial9.ai/blog/spatial9-enterprise-agents-databricks-snowflake-vertex-bedrock

Files

Read the enterprise guide