Google Workspace MCP Server
Enables sending emails, drafting emails, and appending text to Google Docs via MCP tools.
README
Google Workspace MCP Server (Gmail + Google Docs)
A Model Context Protocol (MCP) server that exposes Google Workspace capabilities — specifically Gmail and Google Docs — as standardized MCP tools.
Features
send_email: Send an email immediately via the authenticated Gmail account.draft_email: Create a draft in the authenticated Gmail account without sending.append_to_google_doc: Append text content to the end of an existing Google Doc.
Setup Instructions
1. Google Cloud Project Setup
- Go to the Google Cloud Console.
- Create a new project or select an existing one.
- Navigate to APIs & Services > Library.
- Search for and enable the Gmail API and Google Docs API.
- Navigate to APIs & Services > OAuth consent screen.
- Configure the consent screen (External or Internal).
- Add the following scopes:
https://www.googleapis.com/auth/gmail.sendhttps://www.googleapis.com/auth/gmail.composehttps://www.googleapis.com/auth/documents
- Add your email address as a Test User if your app is in testing mode.
- Navigate to APIs & Services > Credentials.
- Click Create Credentials > OAuth client ID.
- Choose Desktop app as the application type.
- Click Create.
- Download the JSON file and rename it to
credentials.json. Place it in the root of this project.
2. Environment Setup
- Copy
.env.exampleto.env(optional, as defaults are used if not provided). - Install the project dependencies:
pip install -e .
3. First Run (Authentication)
Before an MCP client can use the server, you must authenticate it manually to generate the token.json file.
Run the server directly:
gmail-docs-mcp
This will open a browser window asking you to log in with your Google account and grant the requested permissions. Once completed, a token.json file will be created. You can then stop the server (Ctrl+C).
4. MCP Client Configuration
Configure your MCP client (e.g., Claude Desktop) to run this server. Add the following to your MCP client's configuration file:
{
"mcpServers": {
"google-workspace": {
"command": "gmail-docs-mcp",
"env": {
"GOOGLE_CREDENTIALS_PATH": "/absolute/path/to/credentials.json",
"GOOGLE_TOKEN_PATH": "/absolute/path/to/token.json"
}
}
}
}
Note: Make sure to use absolute paths for the credentials and token files.
Testing
Run unit tests with pytest:
pip install -e ".[dev]"
pytest
Manual Smoke-Test Checklist
- Send test email: Invoke
send_emailwith your own email address to verify receipt. - Create draft: Invoke
draft_emailand check your Gmail Drafts folder. - Append to a doc: Create a test Google Doc, copy its URL or ID, and invoke
append_to_google_doc. Check the document to verify the text was appended at the end.
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。