Access and Search Google Drive Files
The Google Drive MCP server lets Claude search, read, and summarize files directly from a user's Google Drive.
Why it matters
Integrate Google Drive with your AI, enabling it to search for files, read their content, and access cloud storage for enhanced data retrieval and analysis.
Outcomes
What it gets done
Search for files using Drive's query syntax.
Read the content of specific files by ID.
List files within a specified folder.
Access files via resource URIs (e.g., gdrive:///file_id).
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/vb-gdrive | bash Capabilities
Tools your agent gets
Search for files in Google Drive using search queries and Drive search syntax.
Read the contents of a file from Google Drive by file ID.
List files in a Google Drive folder or root directory.
Overview
Google Drive MCP
The Google Drive MCP server lets Claude search, read, and list files from a user's Google Drive, exposing Docs, Sheets, Slides, and PDFs as readable MCP resources. It is an official MCP reference server; its upstream repository is archived. Use it when Claude needs to search, read, or summarize content already stored in a user's Google Drive.
What it does
The Google Drive MCP server integrates Claude with Google Drive, letting it search for files, read document contents, and access cloud storage directly. It exposes three tools: search_files (search Drive using Drive's own search syntax), read_file (read a file's contents by ID), and list_files (list files in a folder, or the root if no folder ID is given). Files are also exposed as MCP resources at gdrive:///<file_id>, supporting Google Docs (exported as text), Google Sheets (exported as CSV), Google Slides (exported as text), PDF files, plain text files, and other formats.
When to use - and when NOT to
Use this connector when Claude needs to search, read, or summarize content already stored in a user's Google Drive - for example, searching for a document by topic and summarizing the most recent match.
It requires a Google Cloud project with the Drive API enabled and OAuth 2.0 desktop credentials configured before use, so it is not a fit for a quick one-off connection without first setting up that Google Cloud Console project. This server is one of the official Model Context Protocol reference implementations, now maintained in the modelcontextprotocol/servers-archived repository, which is archived and no longer receiving updates.
Capabilities
search_files(query) searches Drive with Drive's native search syntax; read_file(file_id) reads a file's content; list_files(folder_id?) lists files in a folder. Files are also readable as MCP resources (gdrive:///<file_id>) across Google Docs, Sheets, Slides, PDFs, and plain text.
npm install -g @modelcontextprotocol/server-gdrive
How to install
Install the server globally with the command above, then add it to your Claude Code settings with npx -y @modelcontextprotocol/server-gdrive as the command. Before first use, create a project in Google Cloud Console, enable the Google Drive API, create OAuth 2.0 credentials of the Desktop application type, download the credentials file, and point the server at it via the GOOGLE_APPLICATION_CREDENTIALS environment variable. The server requests two OAuth scopes: drive.readonly (read file metadata and content) and drive.file (access files created by the app).
Who it's for
Anyone who wants Claude to search, read, and summarize documents already stored in their Google Drive, without manually exporting or copy-pasting file contents into the conversation.
Source README
The Google Drive MCP server provides integration with Google Drive, allowing Claude to search for files, read document contents, and access your cloud storage.
Installation
npm install -g @modelcontextprotocol/server-gdrive
Configuration
Add to your Claude Code settings:
{
"mcpServers": {
"gdrive": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-gdrive"]
}
}
}
Authentication Setup
- Create a project in Google Cloud Console
- Enable the Google Drive API
- Create OAuth 2.0 credentials (Desktop application type)
- Download the credentials file
- Set the path to credentials:
{
"mcpServers": {
"gdrive": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-gdrive"],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/credentials.json"
}
}
}
}
Available Tools
search_files
Search for files in Google Drive.
search_files(query: string): FileList
Parameters:
query- Search query (supports Drive search syntax)
read_file
Read the contents of a file.
read_file(file_id: string): FileContent
list_files
List files in a folder.
list_files(folder_id?: string): FileList
Resources
The server also exposes files as MCP resources:
gdrive:///<file_id>- Access any file by ID- Supports Google Docs, Sheets, and other formats
Supported File Types
- Google Docs (exported as text)
- Google Sheets (exported as CSV)
- Google Slides (exported as text)
- PDF files
- Plain text files
- And more...
Usage Example
Claude, search my Google Drive for documents about
"quarterly report" and summarize the most recent one.
Permissions
The server requires the following OAuth scopes:
https://www.googleapis.com/auth/drive.readonly- Read file metadata and contenthttps://www.googleapis.com/auth/drive.file- Access files created by the app
FAQ
Common questions
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.