Google Toolbox

v1.0.0APIsstable

MCP server for google toolbox

google-toolboxmcpai-integration
Share:
10
Stars
0
Downloads
0
Weekly
0/5

What is Google Toolbox?

Google Toolbox is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for google toolbox

MCP server for google toolbox

This server falls under the APIs category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP server for google toolbox

Use Cases

Google services integration
jikime

Maintainer

LicenseApache 2.0
Languagepython
Versionv1.0.0
UpdatedNov 14, 2025
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y google-toolbox

Manual Installation

npx -y google-toolbox

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Google Toolbox

The Google Toolbox MCP server (py-mcp-google-toolbox) integrates Gmail, Google Calendar, Google Drive, and Google Custom Search into a single MCP server. It exposes tools for reading and sending email, managing calendar events, reading and searching Drive files, and performing Google web searches — all accessible from any MCP-compatible AI client.

Prerequisites

  • Python 3.12 installed
  • uv package manager (curl -LsSf https://astral.sh/uv/install.sh | sh)
  • A Google Cloud project with Gmail, Calendar, Drive, and Custom Search APIs enabled
  • OAuth 2.0 credentials file (credentials.json) downloaded from Google Cloud Console
  • Google API Key and Custom Search Engine ID for web search
1

Clone the repository and set up the environment

Clone the repository and use uv to create a Python 3.12 virtual environment, then install dependencies.

git clone https://github.com/jikime/py-mcp-google-toolbox.git
cd py-mcp-google-toolbox
uv venv -p 3.12
source .venv/bin/activate
uv pip install -r requirements.txt
2

Configure environment variables

Create a .env file in the project root with your Google API credentials. Place credentials.json from the Google Cloud Console in the project directory.

GOOGLE_API_KEY=your_google_api_key
GOOGLE_CSE_ID=your_custom_search_engine_id
GOOGLE_CLIENT_ID=your_oauth_client_id
GOOGLE_CLIENT_SECRET=your_oauth_client_secret
GOOGLE_REFRESH_TOKEN=your_refresh_token
3

Obtain a refresh token

Run the included helper script to complete the OAuth flow and generate your GOOGLE_REFRESH_TOKEN. This opens a browser window for authorization.

uv run get_refresh_token.py
4

Test the server locally

Start the MCP server in development mode to verify tools are listed and credentials are working.

mcp dev server.py
5

Add the server to Claude Desktop config

Register the server in your Claude Desktop configuration file at ~/Library/Application Support/Claude/claude_desktop_config.json.

{
  "mcpServers": {
    "google-toolbox": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/py-mcp-google-toolbox",
        "run",
        "server.py"
      ],
      "env": {
        "GOOGLE_API_KEY": "your_google_api_key",
        "GOOGLE_CSE_ID": "your_cse_id",
        "GOOGLE_CLIENT_ID": "your_client_id",
        "GOOGLE_CLIENT_SECRET": "your_client_secret",
        "GOOGLE_REFRESH_TOKEN": "your_refresh_token"
      }
    }
  }
}

Google Toolbox Examples

Client configuration

Complete claude_desktop_config.json entry for the Google Toolbox MCP server using uv.

{
  "mcpServers": {
    "google-toolbox": {
      "command": "uv",
      "args": [
        "--directory",
        "/Users/yourname/py-mcp-google-toolbox",
        "run",
        "server.py"
      ],
      "env": {
        "GOOGLE_API_KEY": "your_google_api_key",
        "GOOGLE_CSE_ID": "your_cse_id",
        "GOOGLE_CLIENT_ID": "your_client_id",
        "GOOGLE_CLIENT_SECRET": "your_client_secret",
        "GOOGLE_REFRESH_TOKEN": "your_refresh_token"
      }
    }
  }
}

Prompts to try

Example natural language prompts to use with the Google Toolbox MCP server once configured.

- "Show me my 5 most recent unread emails"
- "Search my emails for messages from [email protected]"
- "Send an email to [email protected] with subject 'Meeting notes' and the body attached"
- "List my Google Calendar events for tomorrow"
- "Create a calendar event called 'Team standup' tomorrow at 10am for 30 minutes"
- "Search my Google Drive for files containing 'Q4 report'"
- "Search the web for 'Model Context Protocol best practices'"

Troubleshooting Google Toolbox

credentials.json not found or OAuth flow fails

Download the OAuth 2.0 Client ID credentials as a JSON file from Google Cloud Console (APIs & Services > Credentials) and save it as credentials.json in the project root directory. Ensure the app has the correct scopes enabled for Gmail, Calendar, and Drive.

GOOGLE_CSE_ID or search returns no results

Create a Programmable Search Engine at https://programmablesearchengine.google.com and set it to search the entire web. Copy the Search Engine ID to GOOGLE_CSE_ID and ensure the Google Custom Search JSON API is enabled in your Cloud project.

Token expired or invalid_grant error

Re-run uv run get_refresh_token.py to complete the OAuth flow and obtain a new refresh token. Update GOOGLE_REFRESH_TOKEN in your .env file and restart the MCP server.

Frequently Asked Questions about Google Toolbox

What is Google Toolbox?

Google Toolbox is a Model Context Protocol (MCP) server that mcp server for google toolbox It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Google Toolbox?

Install via npm with the command: npx -y google-toolbox. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with Google Toolbox?

Google Toolbox works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Google Toolbox free to use?

Yes, Google Toolbox is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.

Browse More APIs MCP Servers

Explore all apis servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "google-toolbox": { "command": "npx", "args": ["-y", "google-toolbox"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Google Toolbox?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides