gmail-mcp
Enables searching, reading, sending, drafting, and organizing emails across multiple Google accounts via MCP.
README
gmail-mcp v1.0.0
Unified Multi-Account Google OAuth2 MCP Server for Gmail. Search, read, compose, send, draft, and organize emails across multiple Google accounts seamlessly.
Features (4 Unified Tools)
gmail_search: Search emails with official Gmail search syntax (is:unread,from:boss@corp.com,subject:invoice,newer_than:2d,has:attachment)gmail_read: Read full email content and metadata (subject, sender, body text, HTML, CC, BCC, labels, attachment list)gmail_send: Send emails or create drafts (supports HTML, CC, BCC, thread replies, and file attachments)gmail_manage: Labeling, archiving, trash management, read/unread toggles, permanent deletion, and multi-account inventory
Multi-Account Architecture
A single Google Cloud OAuth client (credentials.json) can authenticate multiple Gmail accounts.
Tokens are stored per-account in ~/.secrets/gmail/tokens/<account_name>.json.
1. Setup Google OAuth Credentials (One-time)
- Create a project in Google Cloud Console.
- Enable the Gmail API.
- Create an OAuth 2.0 Client ID (Desktop Application).
- Download the client secret JSON file and save it as
~/.secrets/gmail/credentials.json(or setGMAIL_CREDENTIALS_JSON).
2. Authenticate Accounts
Run the interactive authorization CLI for each account:
gmail-auth default # Authenticates primary account
gmail-auth work # Authenticates secondary work account
gmail-auth client_x # Authenticates any additional account
List all authenticated accounts:
gmail-auth --list
Installation in MCP Clients (Claude Desktop, OpenCode, Cursor, Windsurf)
Option 1: Instant via uvx (Recommended)
{
"mcpServers": {
"gmail": {
"command": "uvx",
"args": ["--from", "git+https://github.com/Steph-ux/gmail-mcp.git", "gmail-mcp"]
}
}
}
Option 2: Via pip install
pip install git+https://github.com/Steph-ux/gmail-mcp.git
Then in your MCP config:
{
"mcpServers": {
"gmail": {
"command": "gmail-mcp"
}
}
}
Option 3: Local Clone (Development)
{
"mcpServers": {
"gmail": {
"command": "python",
"args": ["D:\\Steph\\script\\gmail-mcp\\server.py"]
}
}
}
Usage Examples
1. Search Messages
# Search in default account:
gmail_search(query='is:unread from:github')
# Search in work account:
gmail_search(account='work', query='subject:invoice newer_than:7d')
2. Read Message
gmail_read(account='work', message_id='18f2a9b4c10d')
3. Send Email or Create Draft
# Send direct email:
gmail_send(
account='default',
to='colleague@example.com',
subject='Project Update',
body_text='Here is the latest status...',
body_html='<h1>Project Update</h1><p>Here is the latest status...</p>'
)
# Create a draft:
gmail_send(
account='work',
to='client@example.com',
subject='Proposal draft',
body_text='Please review the proposal.',
draft=True
)
4. Organize & Manage
# Archive email:
gmail_manage(account='work', action='archive', message_id='18f2a9b4c10d')
# Mark as unread:
gmail_manage(account='default', action='mark_unread', message_id='18f2a9b4c10d')
# Move to trash:
gmail_manage(account='default', action='trash', message_id='18f2a9b4c10d')
# List active accounts:
gmail_manage(action='list_accounts')
Testing
pytest tests
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.