Connect Google Forms to Microsoft Copilot via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Google Forms, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Google Forms + Microsoft Copilot

Let your AI build and read Google Forms: create forms and quizzes, add text, choice, scale, date and other questions, publish or close a form, and read the responses with their answers. Personal Google accounts and Google Workspace.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET

Step 1 — Get credentials

1. Open console.cloud.google.com, pick or create a project, then go to APIs & Services → Library and enable the Google Forms API.
2. Open APIs & Services → OAuth consent screen. Choose Internal if you are on Google Workspace (the simplest option), otherwise External. For External, set the publishing status to In production: while the app is in Testing, Google revokes its refresh tokens after 7 days and the connector stops working every week. For your own account you can click through the "unverified app" warning.
3. Open APIs & Services → Credentials → Create credentials → OAuth client ID, choose the application type Web application and add the authorized redirect URI https://cloud.anythingmcp.com/api/mcp-oauth/callback. If you host AnythingMCP yourself, enter https://your-anythingmcp-host/api/mcp-oauth/callback instead.
4. Paste the client ID into GOOGLE_CLIENT_ID and the client secret into GOOGLE_CLIENT_SECRET, then install the connector.
5. On the connector page, click Authorize with Provider and sign in with the Google account whose forms the AI should use. The refresh token is stored encrypted and access tokens are renewed automatically.

One Google client for all Google connectors: the same Cloud project and OAuth client can serve every Google connector: Gmail, Google Calendar, Google Drive, Google Sheets, Google Docs, Google Slides, Google Forms, Google Contacts, Google Meet, Google Tasks, Search Console, Analytics and Ads. Enable each API in that project, reuse the same client ID and secret, and authorize each connector once. Each one asks only for its own permissions.

Finding a form: paste the form's edit link into the chat; its id is the long string in https://docs.google.com/forms/d/<id>/edit. The link respondents get (/forms/d/e/.../viewform) carries a different id that does not work here. To find forms by name, add the Google Drive connector as well. The connector works on forms your account owns or can edit; forms you can only fill in cannot be read.

Building a form: Google accepts only a title when a form is created. The AI then adds the questions in order: short answer and paragraph, multiple choice, checkboxes and drop-downs, linear scales, ratings, dates and times, grids, section breaks, text blocks, images, YouTube videos and graded quiz questions. It sets the description in a separate step and can turn the form into a quiz or collect respondents' email addresses.

New forms start unpublished: a form created through the API does not accept responses until it is published (Google's default since 30 June 2026). The AI publishes it and opens it for responses with google_forms_set_publish_settings, then gives you the link to share. The same tool closes a form to new responses; the responses received so far stay.

Reading responses: the AI reads the form once to match each answer to its question, and can list only the responses submitted since a given time. Choice answers come back as the option text, file uploads as Google Drive file ids. For very large forms, the linked response spreadsheet is easier to work with through the Google Sheets connector.

Notifications (optional): google_forms_create_watch sends a Cloud Pub/Sub message when a response arrives or the form changes. It needs the Cloud Pub/Sub API and a topic in the same Cloud project as the OAuth client, with the role Pub/Sub Publisher granted to [email protected]. A watch expires after 7 days unless it is renewed with google_forms_renew_watch.

Permissions: the connector asks for https://www.googleapis.com/auth/forms.body (create and edit the forms your account can edit) and https://www.googleapis.com/auth/forms.responses.readonly (read their responses). It does not include Google Drive, so the connector cannot list, search, share or delete form files.

Read-only setup: change the scopes in the connector's OAuth settings to https://www.googleapis.com/auth/forms.body.readonly https://www.googleapis.com/auth/forms.responses.readonly, authorize again and disable google_forms_create_form, google_forms_add_text_question, google_forms_add_choice_question, google_forms_add_item, google_forms_update_form_info, google_forms_update_settings and google_forms_set_publish_settings.

Switched off at install: google_forms_batch_update, which can change and delete questions, and google_forms_delete_watch. Turn them on one by one if the AI needs them.

Changes wait for your yes: before every change the AI tells you what it will create or change and in which form, and waits for your confirmation. A published form is live: respondents see edits at once.

Limits: Google allows each user 150 changes and 180 response lists per minute. Above that it answers 429: wait a minute and try again.

Common errors: 401 means the authorization expired or was revoked (always after 7 days while the consent screen is in Testing): click Authorize with Provider again. 403 PERMISSION_DENIED means the account cannot edit that form, or the scope does not allow the call; 403 "Forms API has not been used in project" means the Google Forms API is not enabled in the Cloud project. 404 usually means the id came from the respondent link instead of the edit link, or the form was deleted. A 400 when adding a question means the position is past the end of the form, or a choice question has duplicate or empty options.

The connector does not share, copy or delete forms (the Google Drive connector does that), cannot edit or delete responses (the Forms API does not allow it) and does not run Apps Script.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Microsoft Copilot

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Microsoft Copilot uses MCP servers through agents built in Copilot Studio: you add AnythingMCP to an agent as a tool, then publish the agent to Microsoft 365 Copilot and Teams. Copilot Studio connects from Microsoft's cloud over Streamable HTTP, which AnythingMCP supports.

1. In Copilot Studio, open your agent (or create one), go to Tools and choose Add a tool → New tool → Model Context Protocol.
2. Enter a Server name (for example AnythingMCP), a Server description that says what the connector does, and the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID. Copilot Studio uses the description to decide when to call the server.
3. Under authentication, choose API key, set Type to Header and the header name to X-API-Key, then select Create.
4. In Add tool, choose Create a new connection, paste an MCP API key from AnythingMCP (MCP Servers → your server → API keys) and select Add to agent.
5. Try it in the agent's Test pane: ask for something that needs the Google Forms tools.
6. Select Publish, then Channels → Microsoft 365 and Microsoft Teams, keep Make agent available in Microsoft Copilot selected and choose Add channel. See agent in Teams installs it for you; in Microsoft 365 Copilot, type @ and pick the agent.

Prefer per-user sign-in? Choose OAuth 2.0 → Dynamic discovery instead of an API key: each user then signs in to AnythingMCP the first time the agent calls it.

Self-hosting? Use your instance's public HTTPS address instead of https://cloud.anythingmcp.com. Copilot Studio connects from Microsoft's cloud, so localhost does not work.

Available tools

Example prompts

• "Create a customer feedback form with a 1 to 5 rating, a multiple-choice question on how they found us and a paragraph for comments, then publish it and give me the link."
• "Summarise this week's responses to the workshop registration form and count the sign-ups per workshop."
• "Turn the onboarding quiz into a graded quiz and collect respondents' email addresses."
• "Close the team survey to new responses; we have enough answers."

FAQ

Which Copilot is this for? Microsoft 365 Copilot at work, through agents built in Copilot Studio. The Microsoft Copilot app for personal accounts has no option to add your own MCP server.

What do I need? A work account with access to Copilot Studio (a license or a trial) to build the agent. People who use it in Microsoft 365 Copilot or Teams need access to the agent: share it with them, or ask an admin to publish it to the organization. If your organization applies data policies to Power Platform connectors, they cover MCP servers too.

The agent doesn't call the tools. Check that the header name is exactly X-API-Key and that the key belongs to the same MCP server as the URL, and make the server description specific: Copilot Studio uses it to decide when to call the server. Publish the agent again after each change; in an open chat, type "start over" to get the new version.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT
• Connect to Cursor
• Connect to Gemini
• Connect to Meta Muse