Skip to main content

Google Workspace Forms MCP server

Let an AI agent build and update surveys, quizzes, and intake forms, then read submissions for routing or analysis. The underlying OpenAPI spec is generated from Google’s Forms API v1 discovery document, so every method and schema Google publishes for that API is represented. That is the full surface area of the API—not every action in the Google Forms UI (for example some sharing or file actions use Drive, and file-upload questions cannot be created via the Forms API). Sharing and trashing the form file still live in Drive.

Setting up an MCP server

This article covers the standard steps for creating an MCP server in AI Gateway and connecting it to an AI client. The steps are the same for every integration — application-specific details (API credentials, OAuth endpoints, and scopes) are covered in the individual application pages.

Before you begin​

You'll need:

  • Access to AI Gateway with permission to create MCP servers
  • API credentials for the application you're connecting (see the relevant application page for what to collect)

Create an MCP server​

Find the API in the catalog​

  1. Sign in to AI Gateway and select MCP Servers from the left navigation.
  2. Select New MCP Server.
  3. Search for the application you want to connect, then select it from the catalog.

Configure the server​

  1. Enter a Name for your server — something descriptive that identifies both the application and its purpose (for example, "Zendesk Support — Prod").
  2. Enter a Description so your team knows what the server is for.
  3. Set the Timeout value. 30 seconds works for most APIs; increase to 60 seconds for APIs that return large payloads.
  4. Toggle Production mode on if this server will be used in a live workflow.
  5. Select Next.

Configure authentication​

Enter the authentication details for the application. This varies by service — see the Authentication section of the relevant application page for the specific credentials, OAuth URLs, and scopes to use.

Configure security​

  1. Set any Rate limits appropriate for your use case and the API's own limits.
  2. Enable Logging if you want AI Gateway to record requests and responses for auditing.
  3. Select Next.

Deploy​

Review the summary, then select Deploy. AI Gateway provisions the server and provides a server URL you'll use when configuring your AI client.

Connect to an AI client​

Once your server is deployed, you'll need to add it to the AI client your team uses. Select your client for setup instructions:

Tips​

  • You can create multiple MCP servers for the same application — for example, a read-only server for reporting agents and a read-write server for automation workflows.
  • If you're unsure which OAuth scopes to request, start with the minimum read-only set and add write scopes only when needed. Most application pages include scope recommendations.
  • You can edit a server's name, description, timeout, and security settings after deployment without redeploying.

Authentication​

Google Forms API uses OAuth 2.0. Create OAuth credentials in Google Cloud Console (Web application) and add the redirect URI https://auth.aigateway.cequence.ai/v1/outbound/oauth/callback. Enable the Google Forms API for your project. The authorization endpoint is https://accounts.google.com/o/oauth2/v2/auth and the token endpoint is https://oauth2.googleapis.com/token.

Typical scopes:

  • https://www.googleapis.com/auth/forms.body — create, read, and edit form definitions (questions, layout, quiz settings).
  • https://www.googleapis.com/auth/forms.body.readonly — read form definitions only.
  • https://www.googleapis.com/auth/forms.responses.readonly — list and read responses.

Drive scopes (https://www.googleapis.com/auth/drive, drive.file, or drive.readonly) are also accepted by many Forms methods when you need alignment with Drive-based access patterns. See Google Forms API authorization and OAuth 2.0 scopes for the full matrix per method.

Available tools​

These tools map to the Google Forms API v1 REST surface exposed by your MCP server.

ToolDescription
Create formCreate a new form (title on create; add items via batch update)
Get formRetrieve the full form, including items, settings, and responder link
Batch update formApply create/update/delete requests for items, questions, and settings in one call
Set publish settingsControl whether the form is published and whether it accepts responses
List form responsesPage through responses with optional timestamp filters
Get form responseFetch a single submission by response ID
List watchesList watches for the form owned by your project
Create watchRegister a watch (for example Pub/Sub delivery for schema or response events)
Delete watchRemove a watch
Renew watchExtend watch validity (typically seven days)

Tips​

Prefer forms.body.readonly plus forms.responses.readonly when an agent only needs to read templates and export submissions—avoid forms.body if the workflow must not change questions or settings.

Create an empty form, then batch-update to add questions; the API only applies certain fields (such as title) on create, so structure is usually built with batchUpdate.

Respect revision IDs when updating forms concurrently; use writeControl in batch updates so conflicting edits fail safely instead of overwriting silently.

Listing responses can be quota-heavy; use filter (RFC3339 timestamps) and pageSize/pageToken to pull only new submissions since your last sync.

Watches expire; renew them on a schedule or automate renewal in your integration. See push notifications for limits and setup.

Sharing and deleting the form file are Drive operations—use the Google Drive integration or Drive API if the agent must change who can edit the form or remove it entirely.