Google Docs & Gmail MCP Server

Google Docs & Gmail MCP Server

Enables appending content to Google Docs and creating email drafts in Gmail via FastAPI endpoints.

Category
访问服务器

README

Google Docs & Gmail MCP Server

A FastAPI-based MCP-style server that provides tools to append content to Google Docs and create email drafts in Gmail.

Project Structure

  • server.py: FastAPI application with endpoints.
  • auth.py: Handles Google OAuth 2.0 flow.
  • docs_tool.py: Contains the logic to append text to Google Docs.
  • gmail_tool.py: Contains the logic to create Gmail drafts.
  • requirements.txt: Python dependencies.

Setup Instructions

1. Google Cloud Console Setup

Before running the application, you need to configure an OAuth client in the Google Cloud Console.

  1. Go to the Google Cloud Console.
  2. Create a new project or select an existing one.
  3. Navigate to APIs & Services > Library and enable the following APIs:
    • Google Docs API
    • Gmail API
  4. Navigate to APIs & Services > OAuth consent screen:
    • Choose External (or Internal if you have a Google Workspace).
    • Fill in the required fields (App name, User support email, Developer contact information).
    • Under Test users, click ADD USERS and enter the email address you will use to test the application.
  5. Navigate to APIs & Services > Credentials:
    • Click CREATE CREDENTIALS > OAuth client ID.
    • Select Desktop app as the Application type.
    • Name it (e.g., "MCP Server Local") and click Create.
    • Download the JSON file, rename it to credentials.json, and place it in the google-mcp-server directory.

2. Install Dependencies

Ensure you have Python 3.7+ installed. Run the following command in the google-mcp-server directory:

pip install -r requirements.txt

3. Initial Authentication

To generate the token.json file, run the auth.py script directly:

python auth.py

This will open a browser window for you to log in with your Google account (ensure you use the email added as a Test User in the consent screen). After granting permission, a token.json file will be created in your directory. You can close the browser window once authenticated.

4. Running the Server

Start the FastAPI server using uvicorn:

uvicorn server:app --reload

Alternatively, run python server.py.

The server will be running at http://127.0.0.1:8000. You can view the API documentation at http://127.0.0.1:8000/docs.

Usage

When you make a request to the server, it will intercept the action and prompt you in the terminal for approval:

--- ACTION REQUIRED ---
Action: Append to Google Doc
Payload: {'doc_id': '...', 'content': '...'}
Approve? (y/n):

You must type y in the terminal where the server is running to proceed.

Example Request: Append to Doc

curl -X 'POST' \
  'http://127.0.0.1:8000/append_to_doc' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
  "doc_id": "YOUR_DOCUMENT_ID",
  "content": "\nThis is a new appended line!"
}'

Example Request: Create Email Draft

curl -X 'POST' \
  'http://127.0.0.1:8000/create_email_draft' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
  "to": "example@example.com",
  "subject": "Test Draft",
  "body": "Hello, this is a draft from MCP Server!"
}'

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