Google Docs & Gmail MCP Server

Google Docs & Gmail MCP Server

Enables appending text to Google Docs and creating Gmail drafts with interactive approval via terminal.

Category
访问服务器

README

Google Docs & Gmail MCP Server

A Python-based MCP-style FastAPI server that integrates with Google Docs and Gmail APIs.

Features

  • Append to Doc (POST /append_to_doc): Appends text content to a Google Document.
  • Create Email Draft (POST /create_email_draft): Creates a Gmail draft.
  • Terminal Approval Gate: Before executing any action, the server outputs the details in the console and blocks waiting for operator approval Approve? (y/n).

Setup Instructions

1. Enable Google APIs & Get Credentials

To run the server, you need to download OAuth client credentials from the Google Cloud Console.

  1. Go to the Google Cloud Console.
  2. Create a new project or select an existing one.
  3. Enable the Google Docs API and Gmail API under APIs & Services > Library.
  4. Configure the OAuth Consent Screen:
    • Choose user type (External or Internal).
    • Add the scopes:
      • https://www.googleapis.com/auth/documents
      • https://www.googleapis.com/auth/gmail.compose
    • Add your Gmail account under Test users.
  5. Create Credentials:
    • Go to APIs & Services > Credentials.
    • Click Create Credentials > OAuth client ID.
    • Select application type Desktop App and name it (e.g., MCP Google Server).
    • Click Create, then download the client secrets JSON.
  6. Rename the downloaded file to credentials.json and place it in the project root directory (google-mcp-server/credentials.json).

Note: credentials.json and token.json (created after authentication) are added to .gitignore to prevent committing them to VCS.


2. Install Dependencies

It is recommended to run in a Python virtual environment:

# Create and activate virtual environment
python3 -m venv .venv
source .venv/bin/activate

# Install required packages
pip install -r requirements.txt

3. Run the Server

Start the FastAPI application:

python server.py
  • On the first run, a browser window will open asking you to log into your Google Account.
  • Grant permissions for the Docs and Gmail scopes.
  • Once completed, the browser will show "The authentication flow has completed..." and token.json will be saved to the directory.
  • Subsequent startups will automatically load credentials from token.json and skip the browser login.

Note: The server binds to 127.0.0.1:8000 to prevent external network access.


API Usage & Verification

1. Append Text to a Google Doc

Sends a request to append text to the Google Document specified by doc_id.

Request:

curl -X POST http://127.0.0.1:8000/append_to_doc \
     -H "Content-Type: application/json" \
     -d '{
       "doc_id": "YOUR_DOCUMENT_ID_HERE",
       "content": "\nThis text was appended via the MCP-style server!"
     }'

Terminal Prompt:

========================================
ACTION REQUESTED: append_to_doc
Payload: {'doc_id': 'YOUR_DOCUMENT_ID_HERE', 'content': '\nThis text was appended via the MCP-style server!'}
========================================
Approve? (y/n): 
  • Type y and press Enter to execute the append operation.
  • Type n (or any other input) to abort. The endpoint returns 403 Forbidden.

2. Create a Gmail Draft

Sends a request to create a draft email.

Request:

curl -X POST http://127.0.0.1:8000/create_email_draft \
     -H "Content-Type: application/json" \
     -d '{
       "to": "recipient@example.com",
       "subject": "Hello from MCP",
       "body": "This is a draft generated by the Google MCP server."
     }'

Terminal Prompt:

========================================
ACTION REQUESTED: create_email_draft
Payload: {'to': 'recipient@example.com', 'subject': 'Hello from MCP', 'body': 'This is a draft generated by the Google MCP server.'}
========================================
Approve? (y/n): 
  • Type y and press Enter to execute the draft creation.
  • Type n (or any other input) to abort. The endpoint returns 403 Forbidden.

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