Custom MCP server connectors

Gemini Enterprise can connect to private data sources and internal tools using the Model Context Protocol (MCP). This allows the AI to securely access and interact with information stored in legacy systems or custom infrastructure where standard connectors are not available.

This feature is available for Gemini Enterprise Standard, Plus, and Frontline editions. It is designed for organisations that need to ground their AI agents in proprietary data or integrate specialised business logic from their own private servers.

To set up a connection, navigate to the Gemini Enterprise page in the Google Cloud console and select Data stores. Click Create data store, search for Custom MCP Server, and provide the server URL and authentication details to register your custom connector.