Authenticate to Google and Google Cloud MCP servers

Google and Google Cloud remote Model Context Protocol (MCP) servers implement the requirements of the MCP authorization specification 2026-07-28 for HTTP-based transports.

In most cases, your AI applications must authenticate to access these servers. Most AI applications that connect to MCP servers let you add authentication in a configuration file. However, not all applications support all Google authentication methods. Consult your application's documentation to understand which methods are supported.

This document describes the different authentication methods and identities that you can use to authenticate to Google and Google Cloud MCP servers.

Some Google and Google Cloud MCP server endpoints don't require authentication. In such cases, no credentials are necessary.

Services that require a principal for Identity and Access Management (IAM) don't support Standard API key credentials for authentication, but services that don't use IAM, like Google Maps, do accept API keys.

The terms AI application and agent are used interchangeably throughout this document, and refer to any program that can instantiate an MCP client.

How MCP requests and authentication work

When your AI application sends an MCP request, the MCP client must authenticate to the MCP server using the authentication method and identity that you supply. If you use your own identity, actions taken by the AI application through MCP requests are attributed to you. Additionally, the MCP client has the same permissions as you do on all resources. If you don't want to use your own credentials, then you can create a separate identity for the application to use to authenticate to the MCP server.

Authentication identities

You can use the following identities to authenticate to Google and Google Cloud MCP servers:

If the principal you're using doesn't have the permissions that you need to accomplish your task, or if you want to use a service account in a development environment, then you can use