Use the Bigtable remote MCP server

Preview

This feature is subject to the "Pre-GA Offerings Terms" in the General Service Terms section of the Service Specific Terms, and the Additional Terms for Generative AI Preview Products. Pre-GA features are available "as is" and might have limited support. For more information, see the launch stage descriptions.

Model Context Protocol (MCP) standardizes the way large language models (LLMs) and AI applications or agents connect to outside data sources. MCP servers let you use their tools, resources, and prompts to take actions and get updated data from their backend service.

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 on MCP architecture, see MCP architecture.

This document describes how to use the Bigtable remote Model Context Protocol (MCP) server to connect to Bigtable from AI applications such as Gemini CLI, agent mode in Gemini Code Assist, Claude Code, or in AI applications that you're developing.

Google and Google Cloud remote MCP servers have the following features and benefits:

• Simplified, centralized discovery.
• Managed 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.

Before you begin

Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

Roles required to select or create a project

• Select a project: Selecting a project doesn't require a specific IAM role—you can select any project that you've been granted a role on.
• Create a project: To create a project, you need the Project Creator role (roles/resourcemanager.projectCreator), which contains the resourcemanager.projects.create permission. Learn how to grant roles.

Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

Go to project selector

Verify that billing is enabled for your Google Cloud project.

Enable the Bigtable Admin API.

Roles required to enable APIs

To enable APIs, you need the Service Usage Admin IAM role (roles/serviceusage.serviceUsageAdmin), which contains the serviceusage.services.enable permission. Learn how to grant roles.

Enable the API

In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

Roles required to select or create a project

• Select a project: Selecting a project doesn't require a specific IAM role—you can select any project that you've been granted a role on.
• Create a project: To create a project, you need the Project Creator role (roles/resourcemanager.projectCreator), which contains the resourcemanager.projects.create permission. Learn how to grant roles.

Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

Go to project selector

Verify that billing is enabled for your Google Cloud project.

Enable the Bigtable Admin API.

Roles required to enable APIs

To enable APIs, you need the Service Usage Admin IAM role (roles/serviceusage.serviceUsageAdmin), which contains the serviceusage.services.enable permission. Learn how to grant roles.

Enable the API

1. Run the following command to install the cbt CLI :

   gcloud components install cbt

Required roles

To get the permissions that you need to enable the Bigtable MCP server, ask your administrator to grant you the following IAM roles on the project where you want to enable the Bigtable MCP server:

• Service Usage Admin (roles/serviceusage.serviceUsageAdmin)
• Make MCP tool calls: MCP Tool User (roles/mcp.toolUser)
• Full access to Bigtable resources: Bigtable Administrator (roles/bigtable.admin)

For more information about granting roles, see Manage access to projects, folders, and organizations.

These predefined roles contain the permissions required to enable the Bigtable MCP server. To see the exact permissions that are required, expand the Required permissions section:

Required permissions

The following permissions are required to enable the Bigtable MCP server:

• serviceusage.mcppolicy.get
• serviceusage.mcppolicy.update
• Make MCP tool calls: mcp.tools.call
• Grants full access to Bigtable resources and lets you assign Bigtable IAM roles: bigtable.admin

You might also be able to get these permissions with custom roles or other predefined roles.

Enable or disable the Bigtable MCP server

You can enable or disable the Bigtable MCP server in a project with the gcloud beta services mcp enable command. For more information, see the following sections.

Enable the Bigtable MCP server in a project

Note: After March 17, 2026, the Bigtable remote MCP server is automatically enabled when you enable Bigtable.

If you're using different projects for your client credentials, such as service account keys, OAuth client ID or API keys, and for hosting your resources, then you must enable the Bigtable service and the Bigtable remote MCP server on both projects.

To enable the Bigtable MCP server in your Google Cloud project, run the following command:

gcloud beta services mcp enable SERVICE \
    --project=PROJECT_ID

Replace the following:

• PROJECT_ID: the Google Cloud project ID.
• SERVICE: the global service name for the Cloud Bigtable Admin API, which is bigtableadmin.googleapis.com.

The Bigtable remote MCP server is enabled for use in your Google Cloud project. If the Bigtable service isn't enabled for your Google Cloud project, you are prompted to enable the service before you enable the Bigtable remote MCP server.

As a security best practice, we recommend that you enable MCP servers only for the services required for your AI application to function.

Disable the Bigtable MCP server in a project

To disable the Bigtable MCP server in your Google Cloud project, run the following command:

gcloud beta services mcp disable SERVICE \
    --project=PROJECT_ID

The Bigtable MCP server is disabled for use in your Google Cloud project.

Authentication and authorization

Bigtable MCP servers use the OAuth 2.0 protocol with Identity and Access Management (IAM) for authentication and authorization. All Google Cloud identities are supported for authentication to MCP servers.

The Bigtable remote MCP server doesn't accept API keys.

We recommend that you create a separate identity for agents using MCP tools so that you can control and monitor access to resources. For more information about authentication, see Authenticate to MCP servers.

Bigtable 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, see Using OAuth 2.0 to access Google APIs.

Bigtable has the following MCP tool OAuth scopes:

Scope URI for gcloud CLI	Description
https://www.googleapis.com/auth/bigtable.admin	Grants full access to Bigtable resources and lets you assign Bigtable IAM roles.

Additional scopes might be required on the resources accessed during a tool call. To view a list of scopes required for Bigtable, see OAuth 2.0 scopes for Bigtable Admin API v2.

Configure an MCP client to use the Bigtable MCP server

AI applications and agents, such as Claude or Gemini CLI, 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. To connect to a remote MCP server, the MCP client must know at a minimum the URL of the remote MCP server.

In your AI application, look for a way to connect to a remote MCP server. You are prompted to enter details about the server, such as its name and URL.

For the Bigtable MCP server, enter the following as required:

• Server name: Bigtable MCP server
• Server URL or Endpoint: https://bigtableadmin.googleapis.com/mcp
• Transport: 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.
• OAuth scope: the OAuth 2.0 scope that you want to use when connecting to the Bigtable MCP server.

For host specific guidance, see the following:

• Claude.ai
• Gemini CLI

For more general guidance, see the following resources:

• Connect to remote MCP servers.
• Configure MCP in an AI application.

Available tools

To view details of available MCP tools and their descriptions for the Bigtable MCP server, see the Bigtable MCP reference.

List tools

Use the MCP inspector to list tools, or send a tools/list HTTP request directly to the Bigtable remote MCP server. The tools/list method doesn't require authentication.

POST /mcp HTTP/1.1
Host: bigtableadmin.googleapis.com
Content-Type: application/json

{
  "jsonrpc": "2.0",
  "method": "tools/list",
}

Sample prompts

You can use the following sample prompts to create or delete Bigtable resources and get information about them:

• "Create an instance INSTANCE_ID in project PROJECT_ID in zone ZONE_ID with NODES nodes."
• "List instances in project PROJECT_ID."
• "Get instance INSTANCE_ID in project PROJECT_ID."
• "Delete instance INSTANCE_ID in project PROJECT_ID."
• "Create a table TABLE_ID in instance INSTANCE_ID in project PROJECT_ID."
• "List tables in instance INSTANCE_ID project PROJECT_ID."
• "Get table TABLE_ID in INSTANCE_ID project PROJECT_ID."
• "Delete table TABLE_ID in instance INSTANCE_ID project PROJECT_ID."

In the prompts, replace the following:

• PROJECT_ID with your Google Cloud project ID.
• INSTANCE_ID with the Bigtable instance ID.
• ZONE_ID with the zone where the cluster runs.
• TABLE_ID with the Bigtable table ID.
• If you want to control the number of nodes in a cluster, replace NODES with the number of nodes that you want in the cluster. If not specified, the default is 1.

Model Armor

Model Armor 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.

Model Armor is only available in specific regional locations. If Model Armor is enabled for a project, and a call to that project comes from an unsupported region, Model Armor makes a cross-regional call. For more information, see Model Armor locations.

Caution: Model Armor logs the entire payload if a request fails. This might expose sensitive information in the logs.

Enable Model Armor

To enable Model Armor on your Google Cloud project, run the following gcloud CLI command:

gcloud services enable modelarmor.googleapis.com \
    --project=PROJECT_ID

Replace PROJECT_ID with your Google Cloud project ID.

Configure protection for Google and Google Cloud remote MCP servers

To protect your MCP tool calls and responses, you create a Model Armor floor setting and then enable MCP content security for your project. 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: Don't enable the prompt injection and jailbreak filter unless your MCP traffic carries natural language data.

1. Set up a Model Armor floor setting with MCP sanitization enabled. For more information, see Configure Model Armor floor settings.

   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:

   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": "HIGH", "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.
   • HIGH: 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 Configure floor settings.

2. For your project, enable Model Armor protection for remote MCP servers.

   gcloud beta services mcp content-security add modelarmor.googleapis.com --project=PROJECT_ID

   Replace PROJECT_ID with your Google Cloud project ID. After you run this command, Model Armor sanitizes all MCP tool calls and responses from the project, regardless of where the calls and responses originate.

3. To confirm that Google MCP traffic is sent to Model Armor, run the following command:

   gcloud beta services mcp content-security get --project=PROJECT_ID
   

   Replace PROJECT_ID with the Google Cloud project ID.

Enable MCP content security

To use content security to protect the MCP traffic between the AI application and Bigtable, run the following gcloud CLI command:

gcloud beta services beta mcp content-security add CONTENT_SECURITY_PROVIDER \
    --project=PROJECT_ID

Replace the following:

• CONTENT_SECURITY_PROVIDER: the name of the content security provider to add, such as modelarmor.googleapis.com.
• PROJECT_ID: the Google Cloud project ID.

Disable Model Armor in a project

To disable Model Armor on a Google Cloud project, run the following command:

gcloud beta services mcp content-security remove modelarmor.googleapis.com \
    --project=PROJECT_ID

Replace PROJECT_ID with the Google Cloud project ID.

Google MCP traffic won't be scanned by Model Armor for the specified project.

Disable scanning MCP traffic with Model Armor

If you want to use Model Armor in a project, and you want to stop scanning Google MCP traffic with Model Armor, 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 won't scan MCP traffic in the project.

Control MCP use with IAM deny policies

Identity and Access Management (IAM) deny policies help you secure Google Cloud remote MCP servers. Configure these policies to block unwanted MCP tool access.

For example, you can deny or allow access based on:

• The principal.
• Tool properties like read-only.
• The application's OAuth client ID.

For more information, see Control MCP use with Identity and Access Management

What's next

• Read the Bigtable MCP reference documentation.
• Learn more about Google Cloud MCP servers.
• Best practices for securing agent interactions with Model Context Protocol.