Google Workspace MCP Server

Google Workspace MCP Server

Enables AI agents to compose and send Gmail emails and append text to Google Docs using the Model Context Protocol.

Category
访问服务器

README

Google Workspace MCP Server

This is a generic Model Context Protocol (MCP) server that enables AI agents (such as Claude Desktop, Cursor, etc.) to compose and send emails via Gmail and append content to Google Docs.


Features

  • Gmail Automation:
    • gmail_create_draft: Compose new draft emails with subject, body, CC, and BCC.
    • gmail_send_email: Send emails directly.
  • Document Management:
    • gdocs_append_text: Append text/paragraphs to the end of a Google Doc.
  • Generic Protocol: Works with any MCP client over standard input/output (stdio).

Prerequisites

  • Node.js (version 18+ recommended)
  • A Google Cloud Console project with the following APIs enabled:
    • Gmail API
    • Google Docs API
  • OAuth 2.0 Credentials (Desktop application type) from Google Cloud.

Setup & Installation

Step 1: Configure Credentials

  1. Go to the Google Cloud Console.
  2. Create or select a project.
  3. Enable the Gmail API and Google Docs API under APIs & Services > Library.
  4. Configure the OAuth Consent Screen (external/internal developer mode, add your email as a test user if in Testing status).
  5. Go to APIs & Services > Credentials > Create Credentials > OAuth client ID.
  6. Set the application type to Desktop app (or Web app with http://localhost:3000/oauth2callback as a redirect URI).
  7. Copy the client ID and client secret.
  8. Create a .env file in the root of this project:
    cp .env.example .env
    
  9. Fill in your Google credentials:
    GOOGLE_CLIENT_ID=your_client_id
    GOOGLE_CLIENT_SECRET=your_client_secret
    GOOGLE_REDIRECT_URI=http://localhost:3000/oauth2callback
    

Step 2: Authorize & Generate Refresh Token

Run the OAuth login flow:

npm run auth
  1. This will print a Google authentication URL. Copy and open it in your browser.
  2. Grant permissions for Gmail (Compose/Send) and Google Docs.
  3. Once completed, the browser will redirect to localhost:3000 showing "Authentication Successful!".
  4. The script will automatically update your .env file with the GOOGLE_REFRESH_TOKEN.

Build the Server

Build the TypeScript files:

npm run build

Integration with Claude Desktop

To connect this server to your Claude Desktop application:

  1. Open your Claude Desktop configuration file:
    • Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%\Claude\claude_desktop_config.json
  2. Add the server config:
    {
      "mcpServers": {
        "google-workspace": {
          "command": "node",
          "args": ["/Users/shubhamthakur/Downloads/nextleap antigravity projects/MCP Server 01./build/index.js"],
          "env": {
            "GOOGLE_CLIENT_ID": "YOUR_CLIENT_ID",
            "GOOGLE_CLIENT_SECRET": "YOUR_CLIENT_SECRET",
            "GOOGLE_REDIRECT_URI": "http://localhost:3000/oauth2callback",
            "GOOGLE_REFRESH_TOKEN": "YOUR_REFRESH_TOKEN"
          }
        }
      }
    }
    
    (Note: Replace the file paths and environment variables with your actual values.)
  3. Restart Claude Desktop.

Available Tools

1. gmail_create_draft

Creates a draft email in the user's Gmail.

  • Parameters:
    • to (string, required): Recipient's email address.
    • subject (string, required): Subject of the email.
    • body (string, required): Email body content (HTML or plain text).
    • cc (string, optional): CC recipient email.
    • bcc (string, optional): BCC recipient email.

2. gmail_send_email

Sends an email immediately.

  • Parameters: Same as gmail_create_draft.

3. gdocs_append_text

Appends text to the end of a specified Google Doc.

  • Parameters:
    • documentId (string, required): The ID of the document (can be parsed from the document URL, e.g. https://docs.google.com/document/d/<documentId>/edit).
    • text (string, required): The text content to append.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选