Learn about new Model Context Protocol (MCP) servers for AlloyDB, Spanner, Cloud SQL, Firestore and Bigtable, as well one for Developer Knowledge.

Google Cloud Platform provides a suite of cloud computing services for building, deploying, and managing applications and infrastructure on Google's global network. Developers can learn about cloud-native development, machine learning, and big data analytics to leverage GCP's scalable and reliable cloud infrastructure for their projects.

Google Cloud

Google Cloud has launched managed MCP (Model Context Protocol) servers for its major database products: AlloyDB, Spanner, Cloud SQL (PostgreSQL, MySQL, SQL Server), Bigtable, and Firestore, plus a Developer Knowledge MCP server. These remote servers require no infrastructure deployment — developers simply configure an endpoint in their agent to gain secure, IAM-authenticated access to operational data. Each database integration exposes specific capabilities: schema management and vector search for AlloyDB, graph and relational queries for Spanner, natural language DB interactions for Cloud SQL, workflow automation for Bigtable, and live document sync for Firestore. All activity is logged via Cloud Audit Logs. The servers follow the open MCP standard, making them compatible with third-party clients like Claude. Future expansions include Looker, BigQuery Migration Service, Memorystore, Pub/Sub, and Kafka.

Managed MCP servers for Google Cloud databases