Google Forms MCP

English | Русский

A1 Google Forms MCP lets an AI app build and manage Google Forms in plain language. Create a survey, choose its questions, publish it when ready, read answers and use notifications for new submissions.

It uses the Google Forms API with your Google account. It distinguishes a draft form from a published form and makes the limits of the Forms API explicit instead of pretending that every form task is possible.

• 13 tools. Inspect form structure and responses, create and edit forms and questions, manage publishing, and configure Pub/Sub watches.

• Publish deliberately. Forms created through the API start without response collection, so they cannot gather answers until you publish them.

• Responses stay untouched. The API can read responses but cannot create or edit them; no tool exists to submit answers.

• Minimal Google scope. It uses forms.body and forms.responses.readonly, without broad Drive access.

Start with a read-only question:

Show me yesterday's replies to the customer feedback form and summarize the free-text answers.

Connect the server · Explore use cases · Open technical documentation

See it working

You: Show me the questions and the response settings of the customer feedback form.

Assistant: Shows the form, its items, whether it is published and whether it accepts responses. Nothing changes.

You: Prepare a required 1–5 rating question called "How was your experience?" following the first question.

Assistant: Shows the target form, position and proposed question, then asks for confirmation before adding it.

You: Confirm.

Assistant: Adds the question to the form. It does not publish or close the form unless you ask separately.

Related MCP server: Google Workspace MCP Server

Contents

• Quick start

• What you can ask it to do

• How a form changes

• What can change

• Getting access

• Configuration

• Data, limits and background work

• Technical documentation

• Support

Quick start

You need Node.js 20+, a Google account and OAuth credentials from a Google Cloud project with the Google Forms API enabled.

1. Prepare Google OAuth access.

2. Add the server to your AI app.

3. Ask the read-only question above.

In the app: open Settings → Plugins → MCP servers, select Add server, then add npx -y mcp-google-forms@latest with GOOGLE_FORMS_CLIENT_ID, GOOGLE_FORMS_CLIENT_SECRET and GOOGLE_FORMS_REFRESH_TOKEN.

From the command line:

codex mcp add google-forms \
  --env GOOGLE_FORMS_CLIENT_ID=your_client_id \
  --env GOOGLE_FORMS_CLIENT_SECRET=your_client_secret \
  --env GOOGLE_FORMS_REFRESH_TOKEN=your_refresh_token \
  -- npx -y mcp-google-forms@latest

codex mcp list

Codex MCP documentation

claude mcp add \
  --env GOOGLE_FORMS_CLIENT_ID=your_client_id \
  --env GOOGLE_FORMS_CLIENT_SECRET=your_client_secret \
  --env GOOGLE_FORMS_REFRESH_TOKEN=your_refresh_token \
  --transport stdio --scope user google-forms \
  -- npx -y mcp-google-forms@latest

claude mcp list

Claude Code MCP documentation

Open Settings → Developer → Edit Config and add:

{
  "mcpServers": {
    "google-forms": {
      "command": "npx",
      "args": ["-y", "mcp-google-forms@latest"],
      "env": {
        "GOOGLE_FORMS_CLIENT_ID": "your_client_id",
        "GOOGLE_FORMS_CLIENT_SECRET": "your_client_secret",
        "GOOGLE_FORMS_REFRESH_TOKEN": "your_refresh_token"
      }
    }
  }
}

If Edit Config is unavailable, edit ~/Library/Application Support/Claude/claude_desktop_config.json on macOS or %APPDATA%\Claude\claude_desktop_config.json on Windows.

Claude Desktop MCP documentation

Add this to ~/.cursor/mcp.json on macOS/Linux or %USERPROFILE%\.cursor\mcp.json on Windows:

{
  "mcpServers": {
    "google-forms": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "mcp-google-forms@latest"],
      "env": {
        "GOOGLE_FORMS_CLIENT_ID": "your_client_id",
        "GOOGLE_FORMS_CLIENT_SECRET": "your_client_secret",
        "GOOGLE_FORMS_REFRESH_TOKEN": "your_refresh_token"
      }
    }
  }
}

Cursor MCP documentation

Run MCP: Open User Configuration and add:

{
  "servers": {
    "google-forms": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "mcp-google-forms@latest"],
      "env": {
        "GOOGLE_FORMS_CLIENT_ID": "${input:forms_client_id}",
        "GOOGLE_FORMS_CLIENT_SECRET": "${input:forms_client_secret}",
        "GOOGLE_FORMS_REFRESH_TOKEN": "${input:forms_refresh_token}"
      }
    }
  },
  "inputs": [
    { "type": "promptString", "id": "forms_client_id", "description": "Google OAuth client ID" },
    { "type": "promptString", "id": "forms_client_secret", "description": "Google OAuth client secret", "password": true },
    { "type": "promptString", "id": "forms_refresh_token", "description": "Google OAuth refresh token", "password": true }
  ]
}

Check it with MCP: List Servers.

VS Code MCP documentation

What you can ask it to do

Inspect a survey and its answers

• How many answers have come in since Monday? Summarize the free-text feedback.

• Show one response by ID.

Build and improve a form

• Create an RSVP form with name, meal preference and arrival date.

• Add a required rating, dropdown, date, time, choice or text question.

• Reorder a question or update a title, description, quiz mode or email collection.

Publish and connect

• Publish a prepared form and show its responder URL.

• Stop accepting new responses without deleting the form.

• Create, renew or remove a Cloud Pub/Sub watch for new submissions.

How a form changes

1. create_form creates a form, which is unpublished by default.

2. Questions are items, identified by their position in the form.

3. Another publishing makes a form available to respondents; closing response collection leaves it published but stops new submissions.

4. Responses are a separate read-only record. The API cannot submit, edit or delete a respondent's answer.

File-upload questions cannot be created through the Forms API, although existing file-upload items can be read. Legacy forms created before Google’s publish model may not support publishing settings.

What can change

The AI client controls confirmation. The server marks reads, writes, and destructive tools/request so the client can distinguish Between as-you-like and forms.

Getting access

Google Forms requires OAuth2; an API key is not enough.

1. Create or select a Google Cloud project and enable the Forms API.

2. Configure the OAuth consent screen and create a Desktop app OAuth client.

3. Authorize the Google account that owns or can edit the forms. The [OAuth 2.0 Playground](https://add-ons.google.com/ Code) can obtain the refresh token with Use your own OAuth credentials enabled.

4. Request all scopes:

https://www.googleapis.com/auth/forms.body
https://www.googleapis.com/auth/forms.responses.readonly

Testing-mode OAuth refresh tokens can expire after seven days. Publish the OAuth app, or use an Internal app in a Workspace domain, when you need long-lived access, treat client secret and refresh token like passwords.

Configuration

* Provide either the OAuth trio or an access token.

Data, limits and background work

• Requests go to Google Forms. The local server refreshes Google OAuth tokens and calls the Forms API. Its anonymous telemetry contains an installation ID, package version, SDK and client versions, and tool names — never OAuth tokens, form contents, tool arguments or prompts. Set ASKDADS_TELEMETRY=0 to opt out.

• Google applies per-minute quotas. Documented limits are 975 reads per project, 450 list_responses calls and 375 writes. On 429, the server uses backoff; reads live after network and 5xx errors, but writes are not replayed after an uncertain failure.

• There is no background polling. The server runs only when called. Pub/Sub option lets your own infrastructure get notified; if your application supports scheduled tasks, it can also check for responses periodically.

Technical documentation

• MCP capabilities catalog — task-oriented pages for every tool.

• ALL tools and inputs

• Development documentation

• Publishing documentation

• Google Forms API reference

A technical threat

Found a bug or need a whole? Request an issue or write in Telegram.

English | Русский

A1 Google Forms MCP lets an AI app build and manage Google Forms in plain language. Create a survey, choose its questions, publish it when ready, read responses and use notifications for new submissions.

It uses the Google Forms API with your Google account. It distinguishes a draft form from a published form and makes the limits of the Forms API explicit instead of pretending that every form task is possible.

• 13 tools. Inspect form structure and responses, create and edit forms and questions, manage publishing, and configure Pub/Sub watches.

• Publish deliberately. Forms created via the API start unpublished, so they cannot collect responses until you publish them.

• Responses stay untouched. The API can read responses but cannot create or edit them; no tools exist to submit answers.

• Minimal Google scopes. It uses forms.bodies and forms.responses.readonly, without expanded Drive access.

Start with a read-only question:

Show me yesterday's responses to the customer feedback form and summarize the free-text answers.

Connect the server · Explore use cases · Open the technical documentation

See it work

You: Show me the questions and the response settings of the customer feedback form.

Assistant: Shows the form, its items, whether it is published for the public and the responses. Nothing changes.

You: Create a required 1–5 rating question called “How was your experience?” following the first question.

Assistant: Shows the target form, position and proposed question, then asks for confirmation before adding.

You: Confirm.

Assistant: Adds the question to the form. It does not publish or close the form unless you ask separately.

Contents

• Quick start

• What you can ask it to do

• How a form changes

• What can change

• Getting access

• Configuration

• Data, limits and background work

• Technical documentation

• Support

Quick start

You need Node.js 20+, a Google account, and OAuth credentials from a Google Cloud project with the Google Forms API enabled.

1. Prepare Google OAuth access.

2. Add the server to your AI app.

3. Ask the read-only question above.

In the app: open Settings → Plugins → MCP servers, select Add server, then add npx -y mcp-google-forms@latest with GOOGLE_FORMS_CLIENT_ID, GOOGLE_FORMS_CLIENT_SECRET and GOOGLE_FORMS_REFRESH_TOKEN.

From the command line:

codex mcp add google-forms \
  --env GOOGLE_FORMS_CLIENT_ID=your_client_id \
  --env GOOGLE_FORMS_CLIENT_SECRET=your_client_secret \
  --env GOOGLE_FORMS_REFRESH_TOKEN=your_refresh_token \
  -- npx -y mcp-google-forms@latest

codex mcp list

Codex MCP documentation

claude mcp add \
  --env GOOGLE_FORMS_CLIENT_ID=your_client_id \
  --env GOOGLE_FORMS_CLIENT_SECRET=your_client_secret \
  --env GOOGLE_FORMS_REFRESH_TOKEN=your_refresh_token \
  --transport stdio --scope user google-forms \
  -- npx -y mcp-google-forms@latest

claude mcp list

Claude Code MCP documentation

Open Settings → Developer → Edit Config and add:

{
  "mcpServers": {
    "google-forms": {
      "command": "npx",
      "args": ["-y", "mcp-google-forms@latest"],
      "env": {
        "GOOGLE_FORMS_CLIENT_ID": "your_client_id",
        "GOOGLE_FORMS_CLIENT_SECRET": "your_client_secret",
        "GOOGLE_FORMS_REFRESH_TOKEN": "your_refresh_token"
      }
    }
  }
}

If Edit Config is unavailable, open ~/Library/Application Support/Claude/claude_desktop_config.json on macOS or %APPDATA%\Claude\claude_desktop_config.json on Windows.

Claude Desktop MCP documentation

Add this to ~/.cursor/mcp.json on macOS/Linux or %USERPROFILE%\.cursor\mcp.json on Windows:

{
  "mcpServers": {
    "google-forms": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "mcp-google-forms@latest"],
      "env": {
        "GOOGLE_FORMS_CLIENT_ID": "your_client_id",
        "GOOGLE_FORMS_CLIENT_SECRET": "your_client_secret",
        "GOOGLE_FORMS_REFRESH_TOKEN": "your_refresh_token"
      }
    }
  }
}

Cursor MCP documentation

Run MCP: Open User Configuration and add:

{
  "servers": {
    "google-forms": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "mcp-google-forms@latest"],
      "env": {
        "GOOGLE_FORMS_CLIENT_ID": "${input:forms_client_id}",
        "GOOGLE_FORMS_CLIENT_SECRET": "${input:forms_client_secret}",
        "GOOGLE_FORMS_REFRESH_TOKEN": "${input:forms_refresh_token}"
      }
    }
  },
  "inputs": [
    { "type": "promptString", "id": "forms_client_id", "description": "Google OAuth client ID" },
    { "type": "promptString", "id": "forms_client_secret", "description": "Google OAuth client secret", "password": true },
    { "type": "promptString", "id": "forms_refresh_token", "description": "Google OAuth refresh token", "password": true }
  ]
}

Check it with MCP: List Servers.

VS Code MCP documentation

What you can ask it to do

a form and its answers

• How many answers have come in since Monday? Summarize the free-text answers.

• Show one response by ID.

Build and improve a form

• Create an RSVP form with name, meal preference and arrival date.

• Add a required rating, dropdown, date, time, choice or text question.

• Reorder a question or update a title, description, quiz mode or email collection.

Publish and connect

• Publish a prepared form and show its responder URL.

• Stop accepting new responses without deleting the form.

• Add, renew or remove a Cloud Pub/Sub to stay being new.

How to change a form

1. create_form creates a form, which starts unlisted by default.

2. Questions are items, identified by their position in the form.

3. Publishing makes a form available; closing responses leaves it listed and stops submissions.

4. Responses are a separate read-only record. The API cannot create, edit or delete a respondent's answer.

File-upload form items cannot be created through the Forms API, although existing file-upload items can be read. Legacy created before Google’s publish model may not

support publishing settings.

Translation: say no.

Getting any two trust one

The AI client controls confirmation. The server marks reads, writes, and destructive so the client can distinguish an inspection from a live changes.

Getting add

Google Forms OAuth is required; an API key is not enough.

1. Create or select a Google Cloud project and enable the Forms API.

2. Configure the OAuth consent screen and create a Desktop app OAuth client.

3. Authorize the Google account that owns or can edit the forms. The OAuth 2.0 Playground can also do its own when the own OAuth credentials are used.

4. Add both scopes:

5. claude mcp add \
     --env GOOGLE_FORMS_CLIENT_ID=your_client_id \
     --env GOOGLE_FORMS_CLIENT_SECRET=your_client_secret \
     --env GOOGLE_FORMS_REFRESH_TOKEN=your_refresh_token \
     --transport stdio --scope user google-forms \
     -- npx -y mcp-google-forms@latest

Testing-mode OAuth refresh tokens can expire after seven days. Publish the OAuth app arena or use an Internal app in a Workspace domain when you need long-lived access. Treat the client secret and refresh token like passwords.

Configuration

& OAuth trio or an access token.

Data, limits and background work

• Requests hit Google Forms. The local server sets and sends Google OAuth tokens to the Forms API. Contains installation ID, SDK version, and client the last revision, not OAuth tokens, but not form contents. Set ASK_TELEMETRY=0 to disable.

• Google applies quotas per minute. The documented limits are 975 reads per project, 450 list_responses calls and 375 writes. On 429 the server uses growth; reads also after network and 5xx errors, but writes, on failure, not on risking.

• There is no background polling. The server runs only when called. Pub/Sub calls can notify your infrastructure about new responses; if your AI app supports scheduled tasks, it can also build simple polling.

Coding documentation

• MCP capabilities catalog — task-oriented pages for every tool.

• All tools and inputs

• Development documentation

• Publishing documentation

• Google Forms API reference

Need help?

Found a bug or need a scenario? Maybe open an issue or write to a Telegram.