cursorbridgemcp

cursorbridgemcp

Leverage Cursor’s powerful new MCP feature with this lightweight Python FastMCP server with a Google Docs agent.

Category
访问服务器

README

MseeP.ai Security Assessment Badge

cursorbridgemcp

Leverage Cursor’s powerful new MCP feature with this lightweight Python FastMCP server with a Google Docs agent. You can easily add additioanl agents

What Else Can You Expose?

The power of this setup lies in its flexibility. Beyond Google Docs, the same pattern applies to virtually any API. By dropping new files into your tools/ folder, you can instantly extend your MCP server to support other services - like Airtable, Slack, Jira, etc… or even internal systems. The beauty of the Model Context Protocol (MCP) is that it standardizes how large language models discover and interact with tools. It tells the LLM what functions exist, what parameters they expect, and what kind of output to anticipate - all without hardcoding behavior into the model itself.

installation notes

You'll need to create a mcp.json file with the JSON code below. Path information formatted for MacOS You'll need to adapt for Windows, replace with location of your code and your_user_name

mcp.json

{
  "mcpServers": {
    "gdocs": {
      "command": "/Users/[your_user_name]/Code/Python/Projects/CursorBridgeMCP/.venv/bin/python",
      "args": ["/Users/[your_user_name]/Code/Python/Projects/CursorBridgeMCP/mcpserver.py"],
      "type": "command"
    }
  }
}

on MacOS this file will go in /[your_user_name]/~/.cursor/mcp.json on windows it's in the user's profile .cursor folder these are hidden folders on both OSs

generating a credentials.json file -

NOTE: you must do this!!! without credentials.json gdoc agent will have no way to authenticate with Google.

  1. If you do not have a Google Cloud Account you can create one for free https://cloud.google.com/gcp

  2. Navigate to the Google Cloud Welcome Page and create a new project https://console.cloud.google.com/welcome

  3. With your new project selected, navigate to https://console.cloud.google.com/apis/credentials

  4. Enable APIs: Google Drive & Google Docs

  5. Create OAuth 2.0 Client ID → Desktop app

  6. Download credentials.json to tools/gdocs/

Testing for successful install

  1. Launch Cursor and go to Cursor > Settings -> Cursor Settings
  2. Click on the MCP Tools tab
  3. You should see an entry for "gdocs" with a little green circle.

If you see a yellow or red circle that means there is some issue

  1. If setup is successful you can now include Google Doc request in your prompts from within cursor. For example after a detailed explanation given to a prompt request, you might follow up with "Please create a new google doc called 'dev notes' and summarize your findings"

Cursor can now use Google Docs!

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