API Gateway now supports Model Context Protocol for AI Agent Tools
Google Cloud's API Gateway can now be configured as a remote Model Context Protocol (MCP) server. This public preview feature enables developers to expose existing REST APIs to AI agents as tools, eliminating the need for backend service modifications. Users can enable MCP by annotating their OpenAPI 3.x specifications with custom Google extensions. This streamlines the integration of existing services with AI agent ecosystems.
Features (1) ›
- API Gateway Enable Model Context Protocol (MCP)
Enable Model Context Protocol (MCP) You can now configure API Gateway to act as a remote Model Context Protocol (MCP) server. This Public Preview feature allows you to expose your existing REST APIs to AI agents as tools, without requiring changes to your backend services. You can enable MCP by annotating your OpenAPI 3.x specification using custom Google extensions. For more information, see Model Context Protocol overview and Configure Model Context Protocol .
https://docs.cloud.google.com/release-notes#September_11_2026
Related releases
- Cluster Toolkit v1.102.0 Enhances GKE with MTC, Flex Volumes, and HPC Capabilities Google Cloud release notes ·
- Google Cloud's Managed Apache Airflow receives new features and improved resilience Google Cloud release notes ·
- Google Cloud Contact Center as a Service: Multiple Bug Fixes Released Google Cloud release notes ·
- Google Addresses Security Vulnerabilities in Slurm for Cluster Toolkit Google Cloud release notes ·
- Google SecOps: Write Permissions Removed from chronicle.readonly OAuth Scope Google Cloud release notes ·
- Google SecOps SIEM: Write Permissions Deprecated from chronicle.readonly Scope Google Cloud release notes ·