Model Armor is a Google Cloud service that helps enhance the security and safety of AI applications. It proactively screens Model Context Protocol (MCP) tool calls and responses to help mitigate risks and support responsible AI practices. Whether you deploy AI in Google Cloud or on other cloud providers, Model Armor helps you protect against malicious input, verify content safety, and identify sensitive data. Use Model Armor to consistently apply safety policies and support compliance across your AI landscape.
Products with Model Armor support
The following table lists the Google and Google Cloud MCP servers that support Model Armor and the behavior and limitations of their integrations.
When Model Armor is enabled and you use the MCP server in a jurisdiction that Model Armor doesn't support:
| Product | The MCP call is sent to a supported jurisdiction. For more information, see Impact of data residency on MCP traffic. |
|---|---|
| Agent Registry | check |
| AlloyDB for PostgreSQL | check |
| BigQuery | check |
| BigQuery Data Transfer Service | check |
| BigQuery Migration Service | check |
| Bigtable | check |
| Cloud Asset Inventory | check |
| Cloud Run | check |
| Cloud Storage | check |
| Customer Experience Agent Studio | check |
| Cloud SQL | check |
| Cloud Logging | check |
| Cloud Monitoring | check |
| Cloud Trace | check |
| Compute Engine | check |
| Database Insights | check |
| Database Center | check |
| Datastream | check |
| Database Migration Service | check |
| Developer Knowledge API | check |
| Error Reporting | check |
| Firestore | check |
| GKE | check |
| Google Security Operations | check |
| Knowledge Catalog | check |
| Managed Service for Apache Spark | check |
| Managed Service for Apache Kafka | check |
| Managed Service for Apache Airflow | check |
| Memorystore | check |
| Oracle Database@Google Cloud | check |
| Pub/Sub | check |
| Spanner | check |
| Gemini Enterprise Agent Platform | check |
| Agent Search | check |