mcpField
M
mcp-google-forms

mcp-google-forms

Local
github.com/KamaruSamaProductivity0Updated 27w ago
Repository

About mcp-google-forms

mcp-google-forms is an MCP server for creating, editing, and inspecting Google Forms. Its tools cover quiz setup and grading, question management, and response retrieval for MCP-compatible clients.

Key features

  1. 01Create and configure quiz forms
  2. 02Add multiple-choice, text, and true/false questions
  3. 03Edit, reorder, and delete questions
  4. 04Check answer keys
  5. 05Read form responses
  6. 06Send raw Forms API updates

Use cases

  1. 01Build a quiz and set its answer key
  2. 02Revise question wording or order
  3. 03Review submitted form responses

MCP support

Exposes 19 tools to MCP clients for managing Google Forms, including form creation and editing, question operations, and response reading.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "kamarusama-mcp-google-forms": {
      "command": "uvx",
      "args": [
        "mcp-google-forms"
      ],
      "env": {
        "GOOGLE_FORMS_MCP_DIR": "<GOOGLE_FORMS_MCP_DIR>"
      }
    }
  }
}
Run commanduvx mcp-google-forms
Environment variables to set
GOOGLE_FORMS_MCP_DIROverride the directory where OAuth credentials.json and token.json are stored (default: ~/.config/google-forms-mcp).

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypimcp-google-forms1.0.1

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-google-forms

MCP server for managing Google Forms — quizzes, grading, images, responses.

Exposes 19 tools for creating, editing, inspecting, and managing Google Forms through the Model Context Protocol. Built for use with Claude Code, Claude Desktop, or any MCP-compatible client.

📖 อ่านภาษาไทย →

Tools at a glance

SectionToolPurpose
Authauth_statusCheck OAuth credential state
Create / metadatacreate_quiz_formNew form in quiz mode
rename_formChange title/description
set_quiz_modeToggle quiz on/off
Readget_formFull form JSON
list_questionsConcise item list
verify_answer_keysDiff current vs expected answer keys
Addadd_true_false_questionSingle T/F question
batch_add_true_falseBulk T/F
add_multiple_choice_questionRadio / checkbox / dropdown
add_text_questionShort or paragraph text
add_section_headerPage break / section
Editupdate_question_titleRename question
update_true_false_answerRe-key a T/F answer
delete_questionRemove item
move_questionReorder
Responseslist_responsesAll submitted responses
get_responseOne response by ID
Escape hatchraw_batch_updateRaw Forms API calls

Install

1. Enable API + get credentials
  1. Go to https://console.cloud.google.com → create/select a project
  2. APIs & Services → Library → enable Google Forms API
  3. OAuth consent screen → External → add yourself as test user
  4. Credentials → Create Credentials → OAuth client ID → Desktop app
  5. Download JSON → save as: 
    ~/.config/google-forms-mcp/credentials.json
2. Register with Claude Code
claude mcp add google-forms -s user -- \
  uv run --directory /path/to/mcp-google-forms python server.py
3. First use

On the first tool call, the server opens a browser for OAuth consent. Token is cached at ~/.config/google-forms-mcp/token.json.

Scopes

  • forms.body — create/edit form structure
  • forms.responses.readonly — read responses
  • drive.file — attach images via Drive

Support the project ❤

If this tool helps your workflow, consider supporting development:

Contact

Copyright © 2026 likezara™. All rights reserved. Developed by Kamaru (pen name).

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.