Google Forms MCP

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 implying that every form task is possible.

• 19 tools. Inspect form structure and responses, create and edit forms and questions, manage publishing, and configure Pub/Sub watches.
• Connects from the conversation. Say "connect Google Forms": the server walks you through the OAuth client, catches Google's redirect on 127.0.0.1 with PKCE and keeps the tokens itself — no config files, no restart.
• Publish deliberately. Forms made through the API start unpublished, so they cannot collect responses until you publish them.
• Responses stay intact. The API can read responses but cannot create or edit them; the server has no tool that submits answers.
• Minimal Google scopes. It uses forms.body and forms.responses.readonly, without broad 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 technical documentation

See it work in a minute

You: Show me the questions and 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?” after 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.

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+ and a Google account. Credentials are not required at install time — the server connects from the conversation.

1. Add the server to your AI app.
2. Say "connect Google Forms": the assistant walks you through creating the OAuth client and approving access without editing config files.
3. Ask the read-only question above.

Codex

In the app: open Settings → MCP servers, select Add server, choose STDIO, enter the command npx -y mcp-google-forms@latest and environment variables GOOGLE_FORMS_CLIENT_ID, GOOGLE_FORMS_CLIENT_SECRET, GOOGLE_FORMS_REFRESH_TOKEN, then select Save and Restart.

From the command line:

codex mcp add google-forms \

-- npx -y mcp-google-forms@latest

codex mcp list

Codex MCP documentation

Claude Code

claude mcp add \

--transport stdio --scope user google-forms \ -- npx -y mcp-google-forms@latest

claude mcp list

Claude Code MCP documentation

Claude Desktop

The current official path is Settings → Extensions. For a custom desktop extension, open Advanced settings → Extension Developer → Install Extension…, select a .mcpb file and follow the prompts.

This repository currently publishes an npm stdio package and does not contain a .mcpb bundle. For Claude Desktop builds that still support local configuration, use the following JSON stdio configuration as a fallback:

{

"mcpServers": { "google-forms": { "command": "npx", "args": ["-y", "mcp-google-forms@latest"] } } }

In those builds, save it to ~/Library/Application Support/Claude/claude_desktop_config.json on macOS or %APPDATA%\Claude\claude_desktop_config.json on Windows.

Claude Desktop MCP documentation

Cursor

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"] } } }

Cursor MCP documentation

VS Code

Run MCP: Open User Configuration and add:

{

"servers": { "google-forms": { "type": "stdio", "command": "npx", "args": ["-y", "mcp-google-forms@latest"] } } }

Check it with MCP: List Servers.

VS Code MCP documentation

What you can ask it to do

Inspect a survey and its answers

• Show this form’s questions, response settings and responder link.
• How many answers arrived 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 notifications

• 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 starts unpublished by default.
2. Questions are items, identified by their position in the form.
3. 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 prompts. The server marks reads, writes and destructive tools so the client can distinguish an inspection from a live change.

Getting access

Google Forms requires OAuth 2.0; an API key is not enough. There are two ways in, and the first one needs no configuration files.

Connect from the chat (recommended)

Say "connect Google Forms" and the assistant runs the flow with you:

1. setup_instructions prints the checklist: create or select a Google Cloud project, enable Google Forms API, configure the consent screen and create a Desktop app OAuth client.
2. Download that client's JSON ("Download JSON") and give the assistant its path — set_client stores it owner-only. The secret never goes through the conversation.
3. start_login returns a Google consent link. Open it on this machine and approve; the code comes back to a one-shot listener on 127.0.0.1 (PKCE), never through the chat.
4. finish_login exchanges the code and saves the tokens to ~/.config/mcp-google-forms/credentials.json (mode 0600).

The tokens are re-read on every call, so the connection works immediately — no restart of the AI app. auth_status shows what is connected, logout revokes and deletes it.

Environment variables (CI, unattended installs)

1. Create or select a Google Cloud project and enable Google 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 obtain the refresh token when Use your own OAuth credentials is enabled.
4. Request both 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 the client secret and refresh token as passwords.

Configuration

Every variable is optional — with none of them the server connects from the chat.

\* 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, AI client and platform versions, and tool names — never OAuth tokens, form data, tool arguments or prompts. For each tool call it also sends the outcome and, on failure, an excerpt of the error text with e-mails, addresses, tokens, numbers of 4+ digits and quoted text replaced by #; a value from your request can appear in it if the error text contains it. Set ASKADS_TELEMETRY=0 to opt out.
• Google applies per-minute quotas. The documented limits are 975 reads per project, 450 list_responses calls and 375 writes. On 429, the server uses backoff; reads also retry after network and 5xx errors, while writes are not replayed after an uncertain failure.
• There is no background polling. The s