Use the Dataform remote MCP server

This document shows you how to use the Dataform remote Model Context Protocol (MCP) server to connect with AI applications including Gemini CLI, ChatGPT, Claude, and custom applications you are developing. You can use the Dataform remote MCP server to perform tasks such as managing code assets like notebooks and saved queries, scheduling and executing pipelines within BigQuery, and troubleshooting execution failures The Dataform remote MCP server is enabled when you enable the Dataform API.

Model Context Protocol (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.

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.

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

If you're using an existing project for this guide, verify that you have the permissions required to complete this guide. If you created a new project, then you already have the required permissions.

Verify that billing is enabled for your Google Cloud project.

Enable the BigQuery and Dataform APIs.

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.

Enable the APIs

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

If you're using an existing project for this guide, verify that you have the permissions required to complete this guide. If you created a new project, then you already have the required permissions.

Verify that billing is enabled for your Google Cloud project.

Enable the BigQuery and Dataform APIs.

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.

Enable the APIs

1. Connect your Dataform repository to a Git provider such as GitHub or GitLab. For more information, see Connect to a third-party Git repository.
2. Configure your AI agent with a valid OAuth token using the BigQuery scope.

Required roles

To get the permissions that you need to use the Dataform MCP server, ask your administrator to grant you the following IAM roles on your Google Cloud project:

• Make MCP tool calls: MCP Tool User (roles/mcp.toolUser)
• Create Dataform repositories, workspaces, and edit files: Dataform Editor (roles/dataform.editor)
• Run BigQuery jobs: BigQuery Job User (roles/bigquery.jobUser)

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

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

Required permissions

The following permissions are required to use the Dataform MCP server:

• Make MCP tool calls: mcp.tools.call
• Create Dataform repositories, workspaces, and edit files:
  • dataform.workspaces.create
  • dataform.workspaces.get
  • dataform.workspaces.list
  • dataform.workspaces.delete
  • dataform.workspaces.readFile
  • dataform.workspaces.writeFile
  • dataform.workspaces.moveFile
  • dataform.workspaces.removeFile
  • dataform.workspaces.queryDirectoryContents
  • dataform.workspaces.searchFiles
  • dataform.workspaces.commit
  • dataform.workspaces.push
  • dataform.workspaces.pull
  • dataform.workspaces.fetchHistory
  • dataform.workspaces.fetchDiff
  • dataform.workspaces.fetchFileGitStatuses
  • dataform.compilationResults.create
  • dataform.compilationResults.get
  • dataform.compilationResults.list
  • dataform.workflowInvocations.create
  • dataform.workflowInvocations.get
  • dataform.workflowInvocations.list
  • dataform.repositories.get
  • dataform.repositories.list
  • dataform.locations.get
  • dataform.locations.list
• Run BigQuery jobs:
  • bigquery.jobs.create
  • bigquery.config.get

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

Authentication and authorization

The Dataform remote MCP server uses 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 Dataform MCP server manages access through the following authentication and authorization mechanisms:

• Discovery (tools/list) requests don't require authentication, which enables agents to identify available Dataform tools without needing prior authorization.
• Execution (tools/call) requests are authenticated using OAuth, requiring the agent to provide a valid OAuth token that uses the BigQuery scope. For more information, see Dataform MCP OAuth scopes.

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

Dataform 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.

To interact with the Dataform MCP server, the agent must use the BigQuery OAuth scope. This scope allows the agent to manage transformation code and trigger executions that run as BigQuery jobs.

Additional scopes might be required on the resources accessed during a tool call. To view a list of scopes required for Dataform, see Dataform API.

Configure an MCP client to use the Dataform 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, 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 Dataform MCP server, do the following:

• Server name: Dataform MCP server

• Server URL or Endpoint: https://dataform.REGION.rep.googleapis.com/mcp

  Replace REGION with the region where your repository is located, for example, us-central1.

• 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 about authentication, see Authenticate to MCP servers.

For application-specific guidance about setting up and connecting to MCP server, see Client-specific guidance.

For more general guidance, see the following resources:

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

Agent capabilities

The Dataform MCP server provides a set of tools that enable AI agents to interact with and debug data transformation workflows by orchestrating Dataform API calls. The server provides tools to do the following:

• Set up single file assets. Agents manage basic resource setups, including repository creation and directory content queries.
• Manage pipelines and releases. Agents manage workflow and release configurations, generate compilation results, and trigger or cancel workflow invocations.
• Troubleshoot and validate. Agents identify why pipelines fail by retrieving compilation results and querying workflow invocation actions.

Available tools

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

List tools

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

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

{
  "jsonrpc": "2.0",
  "method": "tools/list",
  "id": 1
}

Sample prompts

Use the following sample prompts to get information about Dataform resources, orchestrate workflows, or troubleshoot executions:

• "Create a new Dataform repository named REPOSITORY_ID in project PROJECT_ID."
• "Create a new notebook asset in project PROJECT_ID."
• "Read the content of FILE_NAME in my repository."
• "Commit the changes to FILE_NAME in REPOSITORY_ID."
• "Create a workflow configuration that schedules my pipeline to run every day at 8:00 AM."
• "Trigger a new execution for the WORKFLOW_CONFIGURATION_ID workflow configuration."
• "Check the status of my recent pipeline executions and tell me if any failed, including the error details."
• "Show me the details of the specific execution that failed."
• "List all Dataform repositories in the REGION region of project PROJECT_ID."
• "Cancel the workflow invocation named WORKFLOW_INVOCATION_ID in repository REPOSITORY_ID, which is now running."

In the prompts, replace the following:

• FILE_NAME: the name of the file.
• PROJECT_ID: the Google Cloud project ID.
• REGION: the name of the region.
• REPOSITORY_ID: the unique identifier for your Dataform repository, for example, quickstart-repository.
• WORKFLOW_CONFIGURATION_ID: the unique identifier of the workflow configuration.
• WORKFLOW_INVOCATION_ID: the unique identifier for a specific workflow execution. You can get this identifier from the results of a workflowInvocations.list request or from the name field of a workflowInvocations.create response.

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.

Use 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.

When Model Armor is enabled with logging enabled, 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. 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.

Enable Model Armor

You must enable Model Armor APIs before you can use Model Armor.

Console

1. Enable the Model Armor API.

   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.

   Enable the API

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

   At the bottom of the Google Cloud console, a Cloud Shell 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.

   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: 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.

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": "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.

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 deny policies

Identity and Access Management (IAM) deny policies and 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.

What's next

• Read the Dataform MCP reference documentation.
• Learn more about Google Cloud MCP servers.