MCP Gmail Server
Enables users to read unread emails and create drafts in Gmail via the Model Context Protocol. It leverages Google OAuth 2.0 for secure authentication and integrates with tools like Claude Desktop for natural language email management.
README
MCP Gmail Server
A server that uses model context protocol[https://modelcontextprotocol.io/] to read and create drafts of emails from Gmail.
Project setup
Create Oauth client and add secrets:
Create a Google Cloud Project
- Go to https://console.cloud.google.com/
- In the top-left, open the project dropdown and click New Project
- Give your project a name (e.g., Gmail API Demo)
- Click Create Your project is now created; make sure it’s selected in the project dropdown.
Enable the Gmail API
- Go to the API Library: https://console.cloud.google.com/apis/library
- Search for Gmail API
- Click it → Enable
Configure OAuth 2.0 Credentials
-
Navigate to: APIs & Services → Credentials
-
You’ll be prompted to configure the OAuth Consent Screen (if first time creating OAuth credentials)
-
Choose External if users outside your Google Workspace will use it
-
Fill in details
-
Add test users (email addresses allowed to authorize during development)
-
Save the configuration
-
Click Create Credentials → OAuth client ID
-
Choose the application type: Desktop app (for testing/dev)
-
Name it
-
Click Create
You will now receive:
- Client ID
- Client Secret Download them as JSON for use in your code.
Save the JSON as "client_secret_oauth_gcp.json" in the root of this project. (note this should be stored securely and not commited to github.)
Install and run app
Install uv: https://docs.astral.sh/uv/getting-started/installation/
Install dependencies with uv:
uv sync
Start server:
uv run -m src.mcp_server_gmail
Claude desktop
Install Claude Desktop
Set claude_desktop_config.json file to:
{
"mcpServers": {
"gmail": {
"command": "/Users/myname/Documents/Coding/fac-mcp-gmail-server/.venv/bin/python",
"args": [
"-m",
"mcp_server_gmail"
],
"env": {
"PYTHONPATH": "/Users/myname/Documents/Coding/fac-mcp-gmail-server/src"
},
"cwd": "/Users/myname/Documents/Coding/fac-mcp-gmail-server"
}
}
}
Ensuring the directory paths are replaced appropriately with your local directory paths.
Test (manual)
Go to claude desktop
Try the following: "Get last 3 unread emails" "Create draft emails for these"
See /docs/working_examples, for examples screenshots of the mcp server
Features
- Gmail Oauth set up
- MCP server for read and drafting emails on gmail
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。