Google Workspace MCP Server
Enables sending and drafting emails via Gmail and appending content to Google Docs through the Model Context Protocol.
README
Google Workspace MCP Server
A generic Model Context Protocol (MCP) Server that exposes Google Workspace capabilities to AI agents. Currently, it supports sending and drafting emails via Gmail and appending content to Google Docs.
Prerequisites
- Node.js (v18 or higher recommended)
- Google Cloud Project with the following APIs enabled:
- Gmail API
- Google Docs API
Setup Instructions
1. Configure Google Cloud OAuth
- Go to the Google Cloud Console.
- Create a new project or select an existing one.
- Navigate to APIs & Services > Library and enable Gmail API and Google Docs API.
- Navigate to APIs & Services > OAuth consent screen and configure it. Add your email address as a test user if the app is in "Testing" mode.
- Navigate to APIs & Services > Credentials.
- Click Create Credentials > OAuth client ID.
- Select Desktop app as the application type and create it.
- Download the client ID and client secret.
2. Configure Environment Variables
- Copy
.env.exampleto.env:cp .env.example .env - Update
.envwith yourGOOGLE_CLIENT_IDandGOOGLE_CLIENT_SECRET.
3. Install Dependencies
npm install
4. Authenticate
Run the authentication script to generate and save your OAuth tokens locally:
npm run auth
Follow the prompt in your terminal. It will provide a URL for you to visit. Log in with your Google account, authorize the requested scopes, and copy the provided code back into the terminal.
This will generate a .credentials.json file in the root of the project. Keep this file secure and do not commit it to version control.
5. Build and Run Locally
To compile the TypeScript code:
npm run build
To run the MCP server (starts an Express server on port 3000 by default):
npm start
For development, you can use:
npm run dev
6. Deploy to Railway
- Push your repository to GitHub.
- Create a new project on Railway and deploy from your GitHub repo.
- In the Railway Variables dashboard, add the following variables:
GOOGLE_CLIENT_ID: Your Google OAuth Client ID.GOOGLE_CLIENT_SECRET: Your Google OAuth Client Secret.GOOGLE_OAUTH_CREDENTIALS: Copy the entire contents of your local.credentials.jsonand paste it here.
- Railway will automatically build and start the Express server.
Configuring an MCP Client
This server uses Server-Sent Events (SSE) over HTTP, meaning it is meant to be accessed via a URL rather than a local command.
If your AI client supports connecting to remote MCP servers via SSE (like some custom clients or extensions), point it to your Railway URL (or localhost if running locally):
SSE URL: https://your-app-name.up.railway.app/sse
If you are using a client that requires a local executable (like Claude Desktop), you will need a proxy or wrapper that bridges stdio to the remote SSE endpoints, as Claude Desktop currently natively spawns local processes via stdio.
Available Tools
send_email: Sends an email using the authenticated user's Gmail account.draft_email: Creates a draft email in the authenticated user's Gmail account.append_to_doc: Appends text to the end of an existing Google Document.
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。