Google Forms MCP Server
Enables creation and management of Google Forms with support for all 12 question types, response collection, CSV export, and form publishing through OAuth-authenticated API access.
README
Google Forms CLI
Command-line tool for managing Google Forms - create forms, add questions, export responses.
Features
- Full form management - Create, update, delete, duplicate forms
- All question types - 12 Google Forms question types supported
- Response export - Export responses to CSV
- YAML templates - Create complex forms from simple YAML files
- Interactive OAuth wizard - Easy setup for non-technical users
- Cursor Skill - Works as an AI agent skill in Cursor IDE
Quick Start
1. Install
# Clone the repository
git clone https://github.com/maksdizzy/google-forms-cli
cd google-forms-cli
# Install with uv
uv sync
2. Setup OAuth
# Run interactive setup wizard
uv run gforms auth setup
The wizard guides you through:
- Creating OAuth credentials in Google Cloud Console
- Getting a refresh token
- Saving credentials to
.env
3. Use
# List your forms
uv run gforms list
# Create a new form
uv run gforms create "My Survey"
# Add a question
uv run gforms add-question FORM_ID --type MULTIPLE_CHOICE --title "Rate us" --options "1,2,3,4,5"
# Export responses
uv run gforms export FORM_ID --output responses.csv
Commands
Form Management
| Command | Description |
|---|---|
gforms list |
List all forms |
gforms create "Title" |
Create new form |
gforms get FORM_ID |
Get form details |
gforms update FORM_ID |
Update form |
gforms delete FORM_ID |
Delete form |
gforms duplicate FORM_ID |
Copy form |
gforms link FORM_ID |
Get share links |
Questions
| Command | Description |
|---|---|
gforms add-question |
Add question |
gforms delete-question |
Remove question |
gforms move-question |
Reorder question |
gforms add-section |
Add section break |
Responses
| Command | Description |
|---|---|
gforms responses FORM_ID |
List responses |
gforms export FORM_ID |
Export to CSV |
Templates
| Command | Description |
|---|---|
gforms apply template.yaml |
Create from template |
gforms export-template FORM_ID |
Export to YAML |
Question Types
# Text questions
--type SHORT_ANSWER
--type PARAGRAPH
# Choice questions (use --options)
--type MULTIPLE_CHOICE --options "A,B,C"
--type CHECKBOXES --options "X,Y,Z"
--type DROPDOWN --options "1,2,3"
# Scale questions
--type LINEAR_SCALE --low 1 --high 5
--type RATING --high 5
# Other
--type DATE
--type TIME
YAML Templates
Create forms from YAML files:
form:
title: "Customer Feedback"
description: "Share your experience"
questions:
- type: SHORT_ANSWER
title: "Your name"
required: true
- type: MULTIPLE_CHOICE
title: "Satisfaction"
options: [Excellent, Good, Fair, Poor]
required: true
- type: PARAGRAPH
title: "Comments"
Apply with:
uv run gforms apply feedback.yaml
See templates/examples/ for more examples:
feedback_form.yaml- Employee feedback surveyevent_registration.yaml- Event registration formcustomer_satisfaction.yaml- Customer satisfaction survey
OAuth Setup Details
Prerequisites
- Go to Google Cloud Console
- Create a new project
- Enable Google Forms API and Google Drive API
- Create OAuth 2.0 credentials (Desktop application)
Get Refresh Token
Option 1: OAuth Playground (recommended)
- Go to OAuth Playground
- Click ⚙️ Settings → Check "Use your own OAuth credentials"
- Enter your Client ID and Client Secret
- Add scopes:
https://www.googleapis.com/auth/forms.bodyhttps://www.googleapis.com/auth/forms.responses.readonlyhttps://www.googleapis.com/auth/drive.file
- Authorize and exchange for tokens
- Copy the refresh token
Option 2: Interactive wizard
uv run gforms auth setup
For Cursor/AI Agents
This tool is designed to work as a skill for AI agents in Cursor IDE.
See skill.md for complete agent instructions including:
- Quick reference for all commands
- Common workflows
- Error handling
Project Structure
google-forms-cli/
├── src/gforms/
│ ├── cli.py # Typer CLI commands
│ ├── api.py # Google Forms API wrapper
│ ├── auth.py # OAuth + interactive wizard
│ ├── models.py # Pydantic models
│ └── templates.py # YAML template engine
├── templates/
│ └── examples/ # Example YAML templates
├── skill.md # Cursor agent instructions
├── pyproject.toml # Project configuration
└── README.md # This file
Troubleshooting
OAuth Errors:
uv run gforms auth check # Verify credentials
uv run gforms auth setup # Reconfigure if needed
API Errors:
- Verify Form ID with
uv run gforms list - Check API quotas in Google Cloud Console
Security
.envfile is gitignored (never committed)- Refresh token provides account access - keep secure
- Revoke access: https://myaccount.google.com/permissions
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.