# Use the Bigtable remote MCP server
This document shows you how to use the Bigtable remote Model Context Protocol (MCP) server to connect with AI applications including Antigravity, ChatGPT, Claude, and custom applications you are developing. The Bigtable remote MCP servers let you manage Bigtable instances and tables, and query your data. Use the Admin MCP server for administration tasks, and use the Data MCP server to query your tables from your AI application. The Bigtable remote MCP server is enabled when you enable the Bigtable APIs. [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). ## Before you begin 1. Run the following command to install the `cbt` CLI : gcloud components install cbt
### Required roles To get the permissions that you need to use the Bigtable MCP servers, ask your administrator to grant you the following IAM roles on the project where you want to use the Bigtable MCP server: - Make MCP tool calls: [MCP Tool User](https://docs.cloud.google.com/iam/docs/roles-permissions/mcp#mcp.toolUser) (`roles/mcp.toolUser`) - Use the Admin MCP server: [Bigtable Administrator](https://docs.cloud.google.com/iam/docs/roles-permissions/bigtable#bigtable.admin) (`roles/bigtable.admin`) - Use the Data MCP server: [Bigtable Reader](https://docs.cloud.google.com/iam/docs/roles-permissions/bigtable#bigtable.reader) (`roles/bigtable.reader`) For more information about granting roles, see [Manage access to projects, folders, and organizations](https://docs.cloud.google.com/iam/docs/granting-changing-revoking-access). These predefined roles contain the permissions required to use the Bigtable MCP servers. To see the exact permissions that are required, expand the **Required permissions** section: #### Required permissions The following permissions are required to use the Bigtable MCP servers: - Make MCP tool calls: `mcp.tools.call` - Use the Admin MCP server: - `bigtable.instances.create` - `bigtable.instances.delete` - `bigtable.instances.get` - `bigtable.instances.list` - `bigtable.tables.create` - `bigtable.tables.delete` - `bigtable.tables.get` - `bigtable.tables.list` - Use the Data MCP server: `bigtable.instances.executeQuery` You might also be able to get these permissions with [custom roles](https://docs.cloud.google.com/iam/docs/creating-custom-roles) or other [predefined roles](https://docs.cloud.google.com/iam/docs/roles-overview#predefined). ## Authentication and authorization Bigtable 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 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](https://docs.cloud.google.com/mcp/authenticate-mcp). ## 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](https://developers.google.com/identity/protocols/oauth2). 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. | | `https://www.googleapis.com/auth/bigtable.data` | Enables read and write access to data stored in Bigtable tables. | Additional scopes might be required on the resources accessed during a tool call. To view a list of scopes required for Bigtable, see [Bigtable OAuth scopes](https://docs.cloud.google.com/bigtable/docs/oauth-scopes). ## Configure an MCP client to use the Bigtable MCP servers 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 Bigtable MCP servers, enter the following information, as required: - **Server name** : - Bigtable Admin MCP server - Bigtable Data MCP server - **Server URL** or **Endpoint** : - Admin API: https://bigtableadmin.googleapis.com/mcp - Data API: https://bigtable.googleapis.com/mcp - **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 about authentication, see [Authenticate to MCP servers](https://docs.cloud.google.com/mcp/authenticate-mcp). - **OAuth scope** : the [Bigtable OAuth scope](https://docs.cloud.google.com/bigtable/docs/oauth-scopes) that you want to use when connecting to the Bigtable MCP servers. ### 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. 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). ## Available tools To view details of available MCP tools and their descriptions for the Bigtable MCP server, see the [Bigtable MCP reference](https://docs.cloud.google.com/bigtable/docs/reference/admin/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 a Bigtable remote MCP server. The `tools/list` method doesn't require authentication. For the Admin MCP server, send the request to: curl -X POST https://bigtableadmin.googleapis.com/TOOLSET_ENDPOINT \ -H 'Content-Type: application/json' \ -H 'Accept: application/json' \ -H 'MCP-Protocol-Version: MCP_PROTOCOL_VERSION' \ -H 'Mcp-Method: tools/list' \ -d '{ "jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": { "_meta": { "io.modelcontextprotocol/protocolVersion": "MCP_PROTOCOL_VERSION", "io.modelcontextprotocol/clientCapabilities": { "extensions": { "io.modelcontextprotocol/ui": { "mimeTypes": ["text/html;profile=mcp-app"] } } } } } }' For the Data MCP server, send the request to: curl -X POST https://bigtable.googleapis.com/TOOLSET_ENDPOINT \ -H 'Content-Type: application/json' \ -H 'Accept: application/json' \ -H 'MCP-Protocol-Version: MCP_PROTOCOL_VERSION' \ -H 'Mcp-Method: tools/list' \ -d '{ "jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": { "_meta": { "io.modelcontextprotocol/protocolVersion": "MCP_PROTOCOL_VERSION", "io.modelcontextprotocol/clientCapabilities": { "extensions": { "io.modelcontextprotocol/ui": { "mimeTypes": ["text/html;profile=mcp-app"] } } } } } }' Replace the following: - `TOOLSET_ENDPOINT`: the remainder of the MCP endpoint after the service name. For example, for Bigtable, this might be `mcp/toolset-name`. - `MCP_PROTOCOL_VERSION`: the MCP protocol version. For example, `2026-07-28`. ## Sample prompts You can use the following sample prompts to create or delete Bigtable resources and get information about them. ### Sample administrative prompts - "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`. ### Sample prompts to query data - "Execute a query to retrieve up to 10 rows from the table TABLE_ID in instance INSTANCE_ID in project PROJECT_ID." - "Run a SQL query against instance INSTANCE_ID under project PROJECT_ID: `SELECT _key, column_family, value FROM TABLE_ID WHERE row_key LIKE USER_ID`." - "Retrieve data from Bigtable instance INSTANCE_ID, project PROJECT_ID using app profile APP_PROFILE_ID with the query: `SELECT * FROM TABLE_ID WHERE cf1['status'] = 'ERROR'`." In the prompts, replace the following: - TABLE_ID with the Bigtable table ID. - INSTANCE_ID with the Bigtable instance ID. - PROJECT_ID with your Google Cloud project ID. - USER_ID with the pattern or row key of the user that you want to query. - APP_PROFILE_ID with the ID of the app profile. ## 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). ### 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 [Bigtable MCP reference documentation](https://docs.cloud.google.com/bigtable/docs/reference/admin/mcp). - Learn more about [Google Cloud MCP servers](https://docs.cloud.google.com/mcp/overview). - [Best practices for securing agent interactions with Model Context Protocol](https://docs.cloud.google.com/bigtable/docs/secure-agent-interactions-mcp).