Gmail MCP Server
Provides access to Gmail functionalities including listing unread emails, searching via query syntax, and managing messages through archiving or marking as read. It enables MCP clients to securely interact with and organize email data using the Gmail API.
README
Gmail MCP Server
A Model Context Protocol (MCP) server that provides Gmail access for Claude Code and other MCP clients. Built with FastMCP.
Features
- list_unread - List unread emails from inbox
- search - Search emails using Gmail query syntax
- archive - Archive emails (removes from inbox)
- mark_as_read - Mark emails as read without archiving
- get_labels - Get all Gmail labels
Installation
No local installation required! Run directly from GitHub using uvx:
uvx --from git+https://github.com/fred-drake/gmail-mcp gmail-mcp
Setup
1. Create Google Cloud OAuth Credentials
-
Go to Google Cloud Console
-
Create a new project or select an existing one:
- Click the project dropdown at the top of the page
- Click "New Project", give it a name, and create it
- Make sure your new project is selected
-
Enable the Gmail API:
- Navigate to "APIs & Services" > "Library"
- Search for "Gmail API" and click on it
- Click "Enable"
-
Configure the OAuth consent screen (required before creating credentials):
- Go to "APIs & Services" > "OAuth consent screen"
- Select "External" as the user type and click "Create"
- Fill in the required fields:
- App name: Choose any name (e.g., "Gmail MCP")
- User support email: Select your email
- Developer contact email: Enter your email
- Click "Save and Continue"
- On the "Scopes" page, click "Save and Continue" (no changes needed)
- On the "Test users" page:
- Click "Add Users"
- Enter the Gmail address you want to access (this is critical!)
- Click "Add" then "Save and Continue"
- Click "Back to Dashboard"
-
Create OAuth credentials:
- Go to "APIs & Services" > "Credentials"
- Click "Create Credentials" > "OAuth client ID"
- Choose "Desktop app" as the application type
- Give it a name (e.g., "Gmail MCP Desktop")
- Click "Create"
- Click "Download JSON" to save the credentials file
- Store this file securely - you'll need the path for configuration
2. Set Environment Variables
Set the path to your OAuth credentials file:
export GMAIL_MCP_CREDENTIALS_PATH="/path/to/your/credentials.json"
Optionally, customize the token cache location (default: ~/.config/gmail-mcp/token.json):
export GMAIL_MCP_TOKEN_PATH="/custom/path/token.json"
3. Run OAuth Setup
Run the interactive setup to authenticate:
uvx --from git+https://github.com/fred-drake/gmail-mcp gmail-mcp --setup
This will open a browser window for Google OAuth authentication. After authorizing, the token will be cached for future use.
MCP Client Configuration
Claude Code
Add to your Claude Code MCP settings:
{
"mcpServers": {
"gmail": {
"command": "uvx",
"args": ["--from", "git+https://github.com/fred-drake/gmail-mcp", "gmail-mcp"],
"env": {
"GMAIL_MCP_CREDENTIALS_PATH": "/path/to/your/credentials.json"
}
}
}
}
With Custom Token Path
{
"mcpServers": {
"gmail": {
"command": "uvx",
"args": ["--from", "git+https://github.com/fred-drake/gmail-mcp", "gmail-mcp"],
"env": {
"GMAIL_MCP_CREDENTIALS_PATH": "/path/to/your/credentials.json",
"GMAIL_MCP_TOKEN_PATH": "/custom/path/token.json"
}
}
}
}
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
GMAIL_MCP_CREDENTIALS_PATH |
Yes | - | Path to OAuth credentials JSON |
GMAIL_MCP_TOKEN_PATH |
No | ~/.config/gmail-mcp/token.json |
Path to token cache file |
Tool Reference
list_unread
List unread emails from inbox.
Parameters:
max_results(int, optional): Maximum emails to return (1-100). Default: 20.
Returns: List of email objects with id, from, subject, date, snippet, labels, body_preview.
search
Search emails using Gmail query syntax.
Parameters:
query(str): Gmail search query (e.g., "from:user@example.com is:unread")max_results(int, optional): Maximum results (1-100). Default: 20.
Returns: List of matching email objects.
Example queries:
from:notifications@github.com- Emails from GitHubis:unread newer_than:1d- Unread emails from last 24 hourssubject:invoice- Emails with "invoice" in subjecthas:attachment larger:5M- Emails with attachments over 5MB
archive
Archive emails by removing INBOX and UNREAD labels.
Parameters:
message_ids(list[str]): List of message IDs to archive.
Returns: Dict with archived_count, failed_count, and details.
mark_as_read
Mark emails as read without archiving.
Parameters:
message_ids(list[str]): List of message IDs to mark as read.
Returns: Dict with marked_count, failed_count, and details.
get_labels
Get all Gmail labels for the authenticated user.
Returns: List of label objects with id, name, type, and message counts.
Development
Prerequisites
- Python 3.13+
- Nix (optional, for reproducible environment)
Setup with Nix
cd gmail-mcp
nix develop
Setup with pip
cd gmail-mcp
pip install -e ".[dev]"
Running Tests
pytest
Linting
ruff check .
ruff format .
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。