MCP Google Tools Server
Provides tools for drafting, sending, searching, archiving, labeling, and deleting emails, with safety features like draft mode and confirmation.
Provides tools for listing events, finding free time slots, and creating meetings with attendees.
Provides tools for reading, creating, appending text, filling templates, and exporting documents to PDF.
Provides tools for searching, copying, moving, sharing files, and managing permissions.
Provides tools for reading and writing ranges, named ranges, filter views, find and replace, and CSV export.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Google Tools Serversummarize my unread emails"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🔧 MCP Google Tools Server
A full-featured Model Context Protocol server for Google Workspace.
Give your AI assistant real-time access to Drive, Gmail, Calendar, Sheets, Docs, and Apps Script.
English docs · Документация на русском
✨ What it can do
Service | Capabilities |
📁 Google Drive | Search, copy, move, share, manage permissions |
📊 Google Sheets | Read/write ranges, named ranges, filter views, find & replace, CSV export |
📄 Google Docs | Read, create, append text, fill templates, export to PDF |
📧 Gmail | Draft, send, search, archive, label, delete with confirmation |
📅 Google Calendar | List events, find free slots, create meetings with attendees |
⚙️ Apps Script | Read, staged updates, auto-backup, rollback |
🔗 Resources | Attach live Drive / Gmail / Calendar / Sheets / Docs snapshots to AI context |
💬 Prompts | Ready-made AI templates: summarize inbox, analyze spreadsheet, plan week, search files |
🧩 MCP Primitives
This server exposes all three MCP primitive types:
🛠 Tools
50+ executable actions
Called by the AI on demand.
Every tool is annotated with
readOnlyHint / destructiveHint
so clients can warn before risky actions.
📦 Resources
Read-only data snapshots Attach live Google data directly to the AI context window without calling a tool. Supports static URIs and templates.
💬 Prompts
Reusable AI templates Select a prompt in your MCP client to fetch live data and start a structured conversation in one click.
🚀 Quick Start
1 — Install dependencies
pip install -r requirements.txt2 — Set up Google OAuth
Create an OAuth 2.0 Client ID in Google Cloud Console, download the JSON, and note its path.
Full step-by-step guide: docs/AUTH_SETUP.md · docs/ru/AUTH_SETUP.md
3 — Configure the server
cp config.example.yaml config.yaml
# then edit config.yaml — set paths and choose MCP_AUTH_TOKENMCP_AUTH_TOKEN is a secret string you choose. You can think of it as a local activation key for this MCP server, not as a network security layer or authentication mechanism.
The server only checks that this token is configured before it starts handling tools — this is an extra safety step to avoid accidental runs without explicit setup.
Invent any random string, e.g.
MySecretToken_2026!or use a password generator.Recommended length: 16+ characters. Avoid reusing passwords.
Set it in
config.yaml→mcp_auth_token: "your_token"or as the env varMCP_AUTH_TOKEN.
The token is never sent anywhere — it is only checked locally inside the server process. It does not restrict what your AI agent can do once the server is running. For more details, see docs/SECURITY.md / docs/ru/SECURITY.md.
4 — Connect your IDE
Replace <PROJECT_PATH> with the absolute path to this repository and your_token_here with your token.
{
"mcpServers": {
"google-tools": {
"command": "python",
"args": ["<PROJECT_PATH>\\server.py"],
"env": {
"MCP_AUTH_TOKEN": "your_token_here",
"MCP_CONFIG_FILE": "<PROJECT_PATH>\\config.yaml"
}
}
}
}{
"mcpServers": {
"google-tools": {
"command": "python",
"args": ["<PROJECT_PATH>\\server.py"],
"env": {
"MCP_AUTH_TOKEN": "your_token_here",
"MCP_CONFIG_FILE": "<PROJECT_PATH>\\config.yaml"
}
}
}
}Uses
servers(notmcpServers). Requires VS Code 1.102+ and Copilot enabled.
{
"servers": {
"google-tools": {
"type": "stdio",
"command": "python",
"args": ["<PROJECT_PATH>\\server.py"],
"env": {
"MCP_AUTH_TOKEN": "your_token_here",
"MCP_CONFIG_FILE": "<PROJECT_PATH>\\config.yaml"
}
}
}
}Use the same command / args / env. The root key may be mcpServers or servers.
{
"mcpServers": {
"google-tools": {
"command": "python",
"args": ["<PROJECT_PATH>\\server.py"],
"env": {
"MCP_AUTH_TOKEN": "your_token_here",
"MCP_CONFIG_FILE": "<PROJECT_PATH>\\config.yaml"
}
}
}
}5 — Smoke check
After connecting, call get_gmail_profile() in your AI client.
It should return the authenticated Gmail address if OAuth is configured correctly.
📖 Usage Examples
# Verify authentication
Tool: get_gmail_profile
→ Authenticated Gmail address: user@example.com
# Search for files in Drive
Tool: find_files
Arguments: {"query": "name contains 'budget'"}
→ - Budget_2026.xlsx (ID: 1a2b3c...) [spreadsheet]
# Read a Google Sheet
Tool: read_sheet
Arguments: {"spreadsheet_id": "1a2b3c4d5e...", "range_name": "Sheet1!A1:C10"}
→ | Name | Email | Status |
| John | j@corp.io | Active |
# Create a draft email (safe by default — never sends without draft_mode=false)
Tool: send_email
Arguments: {"to": "colleague@example.com", "subject": "Notes", "body_text": "...", "draft_mode": true}
→ EMAIL DRAFT CREATED (ID: r1234...) — saved as draft, not sent.# Recent Drive files (no arguments needed)
Resource URI: gdrive://recent
# Unread inbox snapshot
Resource URI: gmail://inbox
# This week's calendar
Resource URI: gcalendar://upcoming
# Specific spreadsheet range
Resource URI: gsheets://1a2b3c4d5e.../Sheet1!A1:D20
# Specific Google Doc
Resource URI: gdocs://1a2b3c4d5e...Prompt | What it does |
| Fetches recent Gmail messages → ready for AI summary |
| Reads a sheet range → ready for AI analysis / charts |
| Loads calendar events → ready for scheduling suggestions |
| Searches Drive files → ready for organisation advice |
🛡 Safety Features
Feature | Tools affected |
|
|
|
|
Auto dry-run for large ranges |
|
Draft mode by default |
|
Public sharing blocked |
|
Tool annotations | Every tool carries |
⚠️ Your AI agent has access to all data you authorize via OAuth. Use read-only scopes for sensitive accounts. See docs/SECURITY.md.
⚙️ Configuration Reference
config.yaml keys
Key | Env override | Default | Description |
|
| — | Path to OAuth JSON downloaded from Google Cloud |
|
|
| Where the OAuth token is saved after first login |
|
| — | Required. Token to activate the server |
|
| stderr only | Path to a log file (optional) |
|
|
| Log verbosity: |
|
| — | Directory for Apps Script auto-backups |
| — | full access | List of OAuth scopes (see security docs) |
MCP_CONFIG_FILE— points to yourconfig.yaml. Set this in the IDEenvblock.
Environment variables always override config file values.
client_secrets_file: "C:\\Users\\you\\.google\\oauth.keys.json"
token_file: "C:\\Users\\you\\.google\\token.json"
mcp_auth_token: "MySecretToken_2026!"
log_level: "INFO"📦 Full Tool List
Tool | Type | Description |
| read | Search by name or Drive query |
| read | Full Drive query syntax with result limit |
| read | List file permissions |
| write | Create a folder |
| write | Move a file to a folder |
| write | Copy a file |
| write | Share with user/group/domain/anyone |
| destructive | Revoke public access ( |
Tool | Type | Description |
| read | Read a cell range |
| read | Spreadsheet metadata |
| read | Export range to CSV |
| write | Append a row |
| write | Write rows to a range |
| write | Create a new spreadsheet |
| write | Add a new tab/sheet |
| write | Create a filter view |
| write | Create a named range |
| write | Find & replace ( |
| destructive | Clear a range (auto dry-run for large ranges) |
Tool | Type | Description |
| read | Read document text |
| read | Export document as binary PDF |
| write | Create a new document |
| write | Append text |
| destructive | Fill template placeholders ( |
Tool | Type | Description |
| read | Get authenticated email address |
| read | List emails (with optional search query) |
| read | Read a single email |
| read | Search and return brief summary |
| write | Create a draft |
| write | Send or draft an email ( |
| write | Send an existing draft |
| write | Apply a label ( |
| write | Archive a message ( |
| destructive | Delete an email ( |
| destructive | Delete multiple emails ( |
Tool | Type | Description |
| read | List upcoming events |
| read | Find free time slots |
| write | Create an event |
| write | Create meeting with attendees ( |
Tool | Type | Description |
| read | Read project files |
| write | Create a new project |
| write | Stage an update, get |
| write | Execute a staged update (with auto-backup) |
| write | Cancel a pending staged update |
| write | Restore from auto-backup |
📚 Documentation
🇬🇧 English
Document | Description |
Step-by-step Google OAuth setup guide | |
Full tools, resources, and prompts reference | |
OAuth scopes, safety features, best practices | |
Cursor, Windsurf, VS Code, and other IDE setup | |
How this MCP server was built (step-by-step tutorial) |
🇷🇺 На русском
Документ | Описание |
Пошаговая настройка Google OAuth | |
Полный справочник инструментов, ресурсов и промптов | |
OAuth scopes, защиты, рекомендации | |
Настройка Cursor, Windsurf, VS Code и других IDE |
⚠️ Responsibility notice
You are responsible for understanding the risks and consequences of operations performed by this server.
Use it at your own discretion and follow your organization's security policies.
Built with ❤️ using Model Context Protocol · MCP Python SDK
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Artoxem/yet-another-google-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server