This document shows you how to use the Google Kubernetes Engine remote Model Context Protocol (MCP) server to connect with AI applications including Gemini CLI, ChatGPT, Claude, and custom applications you are developing. The GKE remote MCP server provides read access to your GKE and Kubernetes resources. It allows an AI agent to inspect and observe your environment. The Google Kubernetes Engine remote MCP server is enabled when you enable the Google Kubernetes Engine API. [Model Context Protocol](https://modelcontextprotocol.io/docs/getting-started/intro) (MCP) standardizes how large language models (LLMs) and AI applications or agents connect to external data sources. MCP servers let you use their tools, resources, and prompts to take actions and get updated data from their backend service. ## What's the difference between local and remote MCP servers? Local MCP servers : Typically run on your local machine and use the standard input and output streams (stdio) for communication between services on the same device. Remote MCP servers : Run on the service's infrastructure and offer an HTTP endpoint to AI applications for communication between the AI MCP client and the MCP server. For more information about MCP architecture, see [MCP architecture](https://modelcontextprotocol.io/docs/learn/architecture). ## Stateless core With [MCP version 2026-07-28](https://modelcontextprotocol.io/specification/2026-07-28), MCP changes from a bidirectional, stateful protocol to a stateless protocol. Each MCP request is self-describing and can be routed using headers. There isn't a need for the `initialize`/`initialized` handshake or `Mcp-Session-Id` because each request includes all the information needed in HTTP headers or the `_meta` parameter. MCP servers can request additional information required by a tool through [multi-round-trip requests (MRTR)](https://modelcontextprotocol.io/specification/latest/basic/patterns/mrtr). To help route and process requests without parsing the request body, some MCP headers are required, including the following: - Headers that are required by the MCP specification such as the [protocol version header](https://modelcontextprotocol.io/specification/latest/basic/transports/streamable-http#protocol-version-header) and [standard request headers](https://modelcontextprotocol.io/specification/latest/basic/transports/streamable-http#standard-request-headers). - [Custom headers](https://modelcontextprotocol.io/specification/latest/basic/transports/streamable-http#custom-headers-from-tool-parameters) that are defined by the MCP server. These headers are mirrored into HTTP headers from the tool's input schema using the `x-mcp-header` property. For example, an MCP server might define a custom header to specify the Google Cloud region or project ID. For more information about MCP architecture, see the MCP version 2026-07-28 [specification](https://modelcontextprotocol.io/specification/2026-07-28) and [key changes](https://modelcontextprotocol.io/specification/2026-07-28/changelog). For information on the GKE local MCP server, see [GKE MCP server on GitHub](https://github.com/GoogleCloudPlatform/gke-mcp). ## Google and Google Cloud remote MCP servers Google and Google Cloud remote MCP servers have the following features and benefits:
- Simplified, centralized discovery - Managed global or regional HTTP endpoints - Fine-grained authorization - Optional prompt and response security with Model Armor protection - Centralized audit logging For information about other MCP servers and information about security and governance controls available for Google Cloud MCP servers, see [Google Cloud MCP servers overview](https://docs.cloud.google.com/mcp/overview). You might want to use the GKE local MCP server for the following reasons: - Local development and testing - Offline MCP use - Cluster and workload creation, including manifest generation for AI/ML workloads - Local client configuration (using `kubeconfig`) - Query logs - Get cost and security recommendations for your GKE environment For more information about how to use our local MCP server, see [GKE MCP server](https://github.com/GoogleCloudPlatform/gke-mcp). The following sections only apply to the GKE remote MCP server. ## Before you begin
### Required roles The principal that makes calls to the remote MCP server tools needs permissions to access GKE resources. This principal can be a human user or an automated service account. At a minimum, grant the following role on your Google Cloud project: - **MCP Tool User** ([`roles/mcp.toolUser`](https://docs.cloud.google.com/iam/docs/roles-permissions/mcp#mcp.toolUser)): Grants permission to make tool calls to the MCP server endpoint. - **Kubernetes Engine Cluster Viewer** ([`roles/container.clusterViewer`](https://docs.cloud.google.com/iam/docs/roles-permissions/container#container.clusterViewer)): This role provides the read-only access needed for the remote server's tools. Grant this role to: - A **user account** when a person is interacting with the MCP server through a client like the Gemini CLI. - A **service account** when building an autonomous agent or application that calls the MCP server. ## Authentication and authorization GKE remote MCP servers use the [OAuth 2.0](https://developers.google.com/identity/protocols/oauth2) protocol with [Identity and Access Management (IAM)](https://docs.cloud.google.com/iam/docs/overview) for authentication and authorization. All [Google Cloud identities](https://docs.cloud.google.com/docs/authentication/identity-products) are supported for authentication to MCP servers. The GKE remote MCP server does not accept API keys for authentication. We recommend creating a separate identity for agents using MCP tools so that access to resources can be controlled and monitored. For more information on authentication, see [Authenticate to MCP servers](https://docs.cloud.google.com/mcp/authenticate-mcp). ## GKE remote MCP OAuth scopes OAuth 2.0 uses scopes and credentials to determine if an authenticated principal is authorized to take a specific action on a resource. For more information about OAuth 2.0 scopes at Google, read [Using OAuth 2.0 to access Google APIs](https://developers.google.com/identity/protocols/oauth2). GKE has the following MCP tool OAuth scopes: | Scope URI for gcloud CLI | Description | |---|---| | `https://www.googleapis.com/auth/container` | Grants full read-write access to your GKE resources. | | `https://www.googleapis.com/auth/container.read-only` | Grants read-only access to your GKE resources. | | `https://www.googleapis.com/auth/cloud-platform` | Grants broad, read-write access to your Google Cloud projects. | Additional scopes might be required on the resources accessed during a tool call. To view a list of scopes required for GKE, see [GKE API](https://developers.google.com/identity/protocols/oauth2/scopes#container). ## Configure an MCP client to use the GKE MCP server AI applications and agents, such as Claude or Antigravity, can instantiate an MCP client that connects to a single MCP server. An AI application can have multiple clients that connect to different MCP servers. If your application isn't listed in the [client-specific guidance](https://docs.cloud.google.com/mcp/configure-mcp-ai-application#client-specific-guidance), then you can use the following information to connect from most applications. In your AI application, look for a way to add or connect to a remote MCP server. For the GKE MCP server, enter the following information as required: - **Server name**: GKE remote MCP server - **Server URL** or **Endpoint** : https://container.googleapis.com/mcp or another toolset URL, see [Available tools](https://docs.cloud.google.com/kubernetes-engine/docs/how-to/use-gke-mcp#available-tools) - **Transport** : [Streamable HTTP](https://modelcontextprotocol.io/specification/latest/basic/transports/streamable-http) - **Authentication details** : Depending on how you want to authenticate, you can enter your Google Cloud credentials, your OAuth Client ID and secret, or an agent identity and credentials. For more information on authentication, see [Authenticate to MCP servers](https://docs.cloud.google.com/mcp/authenticate-mcp). For application-specific guidance about setting up and connecting to MCP server, see [Client-specific guidance](https://docs.cloud.google.com/mcp/configure-mcp-ai-application#client-specific-guidance). For more general guidance, see the following resources: - [Connect to remote MCP servers](https://modelcontextprotocol.io/docs/develop/connect-remote-servers). - [Configure MCP in an AI application](https://docs.cloud.google.com/mcp/configure-mcp-ai-application). ### Redirect URIs For web-based applications, and some desktop applications, you must allowlist a redirect URI when you create a client ID and secret for authentication. Redirect URIs are used by the authorization server to send tokens to your application. Your application's documentation should specify the redirect URI that you must use. [Custom redirect URIs](https://developers.google.com/identity/protocols/oauth2/native-app#redirect-uri_custom-scheme) aren't supported. ## Available tools To view details of available MCP tools and their descriptions for the GKE MCP server, see the [GKE MCP reference](https://docs.cloud.google.com/kubernetes-engine/reference/mcp). ### List tools Use the [MCP inspector](https://modelcontextprotocol.io/docs/tools/inspector) to list tools, or send a `tools/list` HTTP request directly to the GKE remote MCP server. The `tools/list` method doesn't require authentication. POST /mcp HTTP/1.1 Host: container.googleapis.com Content-Type: application/json { "jsonrpc": "2.0", "method": "tools/list", } ## Sample use cases The following are sample use cases for the GKE remote MCP server: - Inspect the configuration and status of your GKE clusters and node pools. For example, use the prompt: "Show me the details of my 'production-cluster' and list all of its node pools." - View Kubernetes resource configurations and container logs from within a cluster without using kubectl. For example, use the prompt: "Get the YAML for the 'frontend-deployment' in the 'default' namespace." - Monitor the status of long-running GKE operations, such as cluster upgrades. For example, use the prompt: "List all the GKE operations in my project from the last hour." ## Optional security and safety configurations MCP introduces new security risks and considerations due to the wide variety of actions that you can do with the MCP tools. To minimize and manage these risks, Google Cloud offers default settings and customizable policies to control the use of MCP tools in your Google Cloud organization or project. For more information about MCP security and governance, see [AI security and safety](https://docs.cloud.google.com/mcp/ai-security-safety). When using MCP with GKE, it is important to understand the [shared responsibility model](https://docs.cloud.google.com/kubernetes-engine/docs/concepts/shared-responsibility) between you and Google. While Google secures the infrastructure and the MCP server itself, you are responsible for securing the credentials used by the MCP client, defining appropriate IAM policies for those credentials, and monitoring the actions taken by the AI agent. ### Use Model Armor [Model Armor](https://docs.cloud.google.com/model-armor/overview) is a Google Cloud service designed to enhance the security and safety of your AI applications. It works by proactively screening LLM prompts and responses, protecting against various risks and supporting responsible AI practices. Whether you are deploying AI in your cloud environment, or on external cloud providers, Model Armor can help you prevent malicious input, verify content safety, protect sensitive data, maintain compliance, and enforce your AI safety and security policies consistently across your diverse AI landscape. When Model Armor is enabled with [logging enabled](https://docs.cloud.google.com/model-armor/configure-logging), Model Armor logs the entire payload. This might expose sensitive information in your logs. #### MCP request routing to Model Armor Model Armor is available in [certain regions](https://docs.cloud.google.com/model-armor/locations). When Model Armor is enabled and you use an MCP server in a jurisdiction that Model Armor doesn't support, the routing behavior of the call might be different for different MCP servers and might break data residency compliance for in-use and in-transit data. For more information about the behavior of individual MCP servers, see [Model Armor supported products](https://docs.cloud.google.com/mcp/model-armor-supported-products). #### Enable Model Armor You must enable Model Armor APIs before you can use Model Armor. ### Console 1. Enable the Model Armor API, if it is not already enabled. **Roles required to enable APIs** To enable APIs, you need the `serviceusage.services.enable` permission. If you created the project, then you likely already have this permission through the Owner role (`roles/owner`). Otherwise, you can get this permission through the Service Usage Admin role (`roles/serviceusage.serviceUsageAdmin`). [Learn how to grant roles](https://docs.cloud.google.com/iam/docs/granting-changing-revoking-access). [Enable the API](https://console.cloud.google.com/apis/enableflow?apiid=modelarmor.googleapis.com)
2. Select the project where you want to activate Model Armor. ### gcloud Before you begin, follow these steps using the Google Cloud CLI with the Model Armor API: 1. In the Google Cloud console, activate Cloud Shell. [Activate Cloud Shell](https://console.cloud.google.com/?cloudshell=true) At the bottom of the Google Cloud console, a [Cloud Shell](https://docs.cloud.google.com/shell/docs/how-cloud-shell-works) session starts and displays a command-line prompt. Cloud Shell is a shell environment with the Google Cloud CLI already installed and with values already set for your current project. It can take a few seconds for the session to initialize.
2. Run the following command to set the API endpoint for the Model Armor service. ```bash gcloud config set api_endpoint_overrides/modelarmor "https://modelarmor.LOCATION.rep.googleapis.com/" ``` Replace `LOCATION` with the region where you want to use Model Armor.
#### Configure protection for Google and Google Cloud remote MCP servers To help protect your MCP tool calls and responses you can use Model Armor floor settings. A floor setting defines the minimum security filters that apply across the project. This configuration applies a consistent set of filters to all MCP tool calls and responses within the project. > [!TIP] > **Tip:** Don't enable the prompt injection and jailbreak filter unless your MCP traffic carries natural language data. Set up a Model Armor floor setting with MCP sanitization enabled. For more information, see [Configure Model Armor floor settings](https://docs.cloud.google.com/model-armor/configure-floor-settings). > [!NOTE] > **Note:** If the agent and the MCP server are in different projects, you can create floor settings in both projects (the client project and the resource project). In this case, Model Armor is invoked twice, once for each project. See the following example command: ```bash gcloud model-armor floorsettings update \ --full-uri='projects/PROJECT_ID/locations/global/floorSetting' \ --enable-floor-setting-enforcement=TRUE \ --add-integrated-services=GOOGLE_MCP_SERVER \ --google-mcp-server-enforcement-type=INSPECT_AND_BLOCK \ --enable-google-mcp-server-cloud-logging \ --malicious-uri-filter-settings-enforcement=ENABLED \ --add-rai-settings-filters='[{"confidenceLevel": "MEDIUM_AND_ABOVE", "filterType": "DANGEROUS"}]' ``` Replace `PROJECT_ID` with your Google Cloud project ID. Note the following settings: - `INSPECT_AND_BLOCK`: The enforcement type that inspects content for the Google MCP server and blocks prompts and responses that match the filters. - `ENABLED`: The setting that enables a filter or enforcement. - `MEDIUM_AND_ABOVE`: The confidence level for the Responsible AI - Dangerous filter settings. You can modify this setting, though lower values might result in more false positives. For more information, see [Model Armor confidence levels](https://docs.cloud.google.com/model-armor/overview#ma-confidence-levels). #### Disable scanning MCP traffic with Model Armor To stop Model Armor from automatically scanning traffic to and from Google MCP servers based on the project's floor settings, run the following command: gcloud model-armor floorsettings update \ --full-uri='projects/PROJECT_ID/locations/global/floorSetting' \ --remove-integrated-services=GOOGLE_MCP_SERVER Replace `PROJECT_ID` with the Google Cloud project ID. Model Armor doesn't automatically apply the rules defined in this project's floor settings to any Google MCP server traffic. Model Armor floor settings and general configuration can impact more than just MCP. Because Model Armor integrates with services like Vertex AI, any changes you make to floor settings can affect traffic scanning and safety behaviors across all integrated services, not just MCP. ### Control MCP use with IAM policies Identity and Access Management (IAM) [deny policies](https://docs.cloud.google.com/iam/docs/deny-overview) and [allow policies](https://docs.cloud.google.com/iam/docs/allow-policies) help you secure Google Cloud and Google MCP servers. You can combine multiple criteria to build customized security and governance policies by allowing or denying access based on the following: - The principal. - Tool properties like the read-only attribute. - The service name or tool name. - The application's OAuth client ID. For more information, see [Control MCP use with Identity and Access Management](https://docs.cloud.google.com/mcp/control-mcp-use-iam). ## What's next - Read the [GKE remote MCP reference documentation](https://docs.cloud.google.com/kubernetes-engine/reference/mcp). - Learn more about [Google Cloud MCP servers](https://docs.cloud.google.com/mcp/overview).