Google Docs & Gmail MCP Server
Enables AI agents to create and edit Google Docs and draft Gmail emails through natural language.
README
Google Docs & Gmail MCP Server
An MCP (Model Context Protocol) server that enables AI agents (e.g., Claude Desktop) to interact with Google Docs and Gmail — creating documents, appending content, replacing placeholders, and drafting emails.
Project Structure
MCP/
├── src/
│ ├── index.ts # MCP server entry point (all tool handlers)
│ ├── auth.ts # One-time OAuth 2.0 token generation script
│ ├── googleClient.ts # Centralized authenticated Google API clients
│ └── tools/
│ ├── docsTools.ts # Google Docs & Drive tool implementations
│ └── gmailTools.ts # Gmail draft tool implementations
├── credentials.json # ← You must download this from Google Cloud Console
├── token.json # ← Generated automatically by: npm run auth
├── claude_desktop_config.json # Claude Desktop MCP server configuration
├── package.json
├── tsconfig.json
├── .env.example
└── .gitignore
Getting Started
Prerequisites
- Node.js v18+
- A Google account with access to Google Workspace (Docs + Gmail)
Step 1: Google Cloud Console Setup
- Go to https://console.cloud.google.com/
- Create a new project (e.g.,
MCP-Server) - Enable the following APIs:
- Google Docs API
- Google Drive API
- Gmail API
- Go to APIs & Services → Credentials
- Click Create Credentials → OAuth 2.0 Client ID
- Application Type: Desktop App
- Name:
MCP Server
- Download the JSON file and rename it to
credentials.json - Place
credentials.jsonin the project root:C:\Users\Vaibhav Singh\Desktop\MCP\
Step 2: Authorize the Application (one-time)
powershell -ExecutionPolicy Bypass -Command "npm run auth"
This will:
- Print a Google authorization URL
- You open the URL, log in, and paste the authorization code back
token.jsonis saved automatically
Step 3: Test the MCP Server
# Start the server directly
powershell -ExecutionPolicy Bypass -Command "npm run dev"
# Or launch the MCP Inspector UI for testing
powershell -ExecutionPolicy Bypass -Command "npm run inspect"
Step 4: Connect to Claude Desktop (Phase 5)
Copy the contents of claude_desktop_config.json into your Claude Desktop configuration file, located at:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json
Then restart Claude Desktop. You should see 7 tools available from this MCP server.
Available Tools
| Tool | Description |
|---|---|
create_document |
Creates a new Google Doc and returns ID + URL |
search_documents |
Searches Google Drive for Docs by name |
append_text |
Appends text to the end of a document |
insert_at_placeholder |
Replaces {{placeholder}} text in a document |
read_document |
Returns the full text content of a document |
create_gmail_draft |
Creates a Gmail draft email (To, Subject, Body, CC) |
list_gmail_drafts |
Lists recent Gmail drafts |
Example Prompts for Claude
"Create a new Google Doc titled 'Q3 Report' and append a summary of our meeting."
"Search for a document called 'Meeting Notes' and append today's agenda."
"Create a Gmail draft to john@example.com with subject 'Project Update' and a professional body."
"Find the document 'Email Log' and replace the placeholder
{{latest_draft}}with the email I just dictated."
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。