GDrive MCP Server
Enables Claude to perform comprehensive read and write operations on Google Docs, Sheets, and Drive folders. It supports file management, content searching, and provides resource access via custom URI schemes for seamless project context integration.
README
GDrive MCP Server
MCP server for Google Drive read/write operations. Enables Claude to use Google Docs as project context files.
Works with: Claude Desktop (stdio) AND Claude Browser (HTTP/SSE)
Features
- Read Google Docs (export to text/markdown)
- Write/Update Google Docs (append or replace content)
- Google Sheets (read/update cells, append rows)
- Folder Operations (create, list, search)
- File Upload/Download (any format)
Setup
1. Google Cloud Project
- Go to Google Cloud Console
- Create a new project (or use existing)
- Enable APIs:
- Google Drive API
- Google Docs API
- Google Sheets API
- Create credentials → Service Account
- Download JSON key file
- Share your GDrive folders/files with the service account email (looks like:
name@project.iam.gserviceaccount.com)
2. Claude Desktop (Local)
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"gdrive": {
"command": "npx",
"args": ["-y", "tsx", "https://raw.githubusercontent.com/shaikh3/gdrive-mcp-server/main/src/index.ts"],
"env": {
"GOOGLE_SERVICE_ACCOUNT_KEY": "{...your key...}"
}
}
}
}
3. Claude Browser (Web) - Deploy to Vercel
For Claude browser, you need to deploy the server publicly.
Deploy to Vercel
- Fork this repo to your GitHub
- Connect to Vercel:
npm i -g vercel vercel - Add environment variable in Vercel Dashboard:
GOOGLE_SERVICE_ACCOUNT_KEY= your JSON key contentMCP_TRANSPORT=http
- Get your deployed URL:
https://your-app.vercel.app
Claude Browser Config
In Claude browser (claude.ai), you need an MCP client that connects to your deployed endpoint. Configure it with:
Server URL: https://your-app.vercel.app/sse
Or if using a custom MCP client:
{
"mcpServers": {
"gdrive": {
"url": "https://your-app.vercel.app/sse"
}
}
}
Environment Variables
| Variable | Required | Description |
|---|---|---|
GOOGLE_SERVICE_ACCOUNT_KEY |
Yes* | JSON content of service account key |
GOOGLE_SERVICE_ACCOUNT_PATH |
Alt* | Path to JSON key file |
MCP_TRANSPORT |
No | stdio (default) or http |
PORT |
No | HTTP port (default: 3000) |
*One of KEY or PATH is required
Tools
Document Operations
gdrive_doc_read
Read a Google Doc as text/markdown.
{
"fileId": "1ABC123...",
"format": "markdown"
}
gdrive_doc_write
Write/replace content in a Google Doc.
{
"fileId": "1ABC123...",
"content": "# Project Context\n\nUpdated from chat...",
"mode": "replace"
}
gdrive_doc_create
Create a new Google Doc.
{
"title": "Claude Project - Context",
"folderId": "1FolderID...",
"content": "Initial project context..."
}
Sheet Operations
gdrive_sheet_read
Read range from Google Sheet.
{
"spreadsheetId": "1SheetID...",
"range": "Sheet1!A1:D10"
}
gdrive_sheet_write
Write to range in Google Sheet.
{
"spreadsheetId": "1SheetID...",
"range": "Sheet1!A1",
"values": [["Name", "Status"], ["Task 1", "Done"]]
}
Folder Operations
gdrive_folder_create
Create a new folder.
{
"name": "Claude Projects",
"parentId": "root"
}
gdrive_search
Search for files/folders.
{
"query": "name contains 'Project' and mimeType = 'application/vnd.google-apps.document'"
}
Development
# Install dependencies
npm install
# Build
npm run build
# Run locally (stdio mode - for Claude Desktop)
npm start
# Run in HTTP mode (for Claude Browser)
MCP_TRANSPORT=http npm start
# Dev mode
npm run dev
Your Use Case: Project Context Files
Claude Desktop:
You: "Update my project context doc with what we just discussed"
Claude: *calls gdrive_doc_write on your context file*
Claude Browser:
You: "Read the project context from gdrive://doc/1ABC123..."
Claude: *fetches and reads via deployed MCP server*
The doc updates in real-time - accessible from any chat, any device.
License
MIT
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.