mcp-google
MCP server for Google APIs — Gmail and Calendar tools for LLM agents.
README
mcp-google
MCP server for Google APIs — Gmail and Calendar tools for LLM agents.
Install
# Run directly with uvx (no install needed)
uvx mcp-google
# Or install with pip
pip install mcp-google
Environment Variables
| Variable | Description |
|---|---|
GOOGLE_CLIENT_ID |
OAuth2 client ID from Google Cloud Console |
GOOGLE_CLIENT_SECRET |
OAuth2 client secret |
GOOGLE_ACCOUNTS_JSON |
JSON array of account configs (see below) |
GOOGLE_ACCOUNTS_JSON format
[
{"email": "personal@gmail.com", "refresh_token": "1//..."},
{"email": "work@company.com", "refresh_token": "1//..."}
]
The first account in the array is used as default when no account parameter is specified.
Tools
Phase 1 — Read-only
| Tool | Parameters | Description |
|---|---|---|
gmail_list_unread |
account?, max_results? |
List unread emails (subject, sender, date, snippet) |
gmail_get_message |
message_id, account? |
Get full email content by ID |
calendar_today |
account? |
Today's events |
calendar_week |
account? |
This week's agenda |
Phase 2 — Write
| Tool | Parameters | Description |
|---|---|---|
gmail_send |
to, subject, body, account? |
Send an email |
calendar_create_event |
title, start, end, account? |
Create a calendar event |
OAuth Setup
- Go to Google Cloud Console
- Create a project (or select existing)
- Enable Gmail API and Google Calendar API
- Go to Credentials > Create Credentials > OAuth 2.0 Client ID
- Application type: Desktop app
- Note the Client ID and Client Secret
- Configure OAuth consent screen with required scopes:
https://www.googleapis.com/auth/gmail.readonlyhttps://www.googleapis.com/auth/gmail.sendhttps://www.googleapis.com/auth/calendar.readonlyhttps://www.googleapis.com/auth/calendar.events
- Obtain refresh tokens for each account using the OAuth2 flow
- Set environment variables (copy
.env.exampleto.envand fill in values)
Obtaining Refresh Tokens
Use the Google OAuth Playground or run a local OAuth flow:
# Quick method via oauth2l
pip install google-auth-oauthlib
python -c "
from google_auth_oauthlib.flow import InstalledAppFlow
flow = InstalledAppFlow.from_client_config(
{'installed': {'client_id': 'YOUR_CLIENT_ID', 'client_secret': 'YOUR_SECRET', 'auth_uri': 'https://accounts.google.com/o/oauth2/auth', 'token_uri': 'https://oauth2.googleapis.com/token'}},
scopes=['https://www.googleapis.com/auth/gmail.readonly', 'https://www.googleapis.com/auth/gmail.send', 'https://www.googleapis.com/auth/calendar.readonly', 'https://www.googleapis.com/auth/calendar.events']
)
creds = flow.run_local_server(port=0)
print(f'Refresh token: {creds.refresh_token}')
"
Running
# As MCP server (stdio transport)
mcp-google
# Or directly
python -m mcp_google.server
Claude Desktop config
{
"mcpServers": {
"google": {
"command": "mcp-google",
"env": {
"GOOGLE_CLIENT_ID": "...",
"GOOGLE_CLIENT_SECRET": "...",
"GOOGLE_ACCOUNTS_JSON": "[{\"email\": \"me@gmail.com\", \"refresh_token\": \"...\"}]"
}
}
}
}
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.