cursorbridgemcp
Leverage Cursor’s powerful new MCP feature with this lightweight Python FastMCP server with a Google Docs agent.
README
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.
-
If you do not have a Google Cloud Account you can create one for free https://cloud.google.com/gcp
-
Navigate to the Google Cloud Welcome Page and create a new project https://console.cloud.google.com/welcome
-
With your new project selected, navigate to https://console.cloud.google.com/apis/credentials
-
Enable APIs: Google Drive & Google Docs
-
Create OAuth 2.0 Client ID → Desktop app
-
Download credentials.json to tools/gdocs/
Testing for successful install
- Launch Cursor and go to Cursor > Settings -> Cursor Settings
- Click on the MCP Tools tab
- 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
- 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!
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
