Best for
- Individuals or teams that need an assistant to search Google Drive documents and sheets
- Knowledge workflows using cloud documents as grounded question-answering context
Cloud-document retrieval is valuable, but OAuth setup and document exposure require strict control; community maintenance and the real authorization flow still need runtime verification.
Strongest · Reliability 13/20 Weakest · Maintenance 9/20
Reviewed by an editorListed 2026-07-13
Read the FMRS scoring method →Runtime:Node.js
GDRIVE_CREDENTIALS_PATH
Path to the Google OAuth credentials file (e.g. ./credentials.), obtained by creating an OAuth client in Google Cloud Console and downloading it.
Create OAuth credentials in Google Cloud Console, download credentials.json, and complete the authorization flow once.
{
"mcpServers": {
"gdrive": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-gdrive"],
"env": {
"GDRIVE_CREDENTIALS_PATH": "./credentials.json"
}
}
}
}
Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.
{
"servers": {
"gdrive": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-gdrive"
],
"env": {
"GDRIVE_CREDENTIALS_PATH": "./credentials.json"
}
}
}
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
claude mcp add gdrive -e GDRIVE_CREDENTIALS_PATH=./credentials.json -- npx -y @modelcontextprotocol/server-gdrive
Run it in a terminal; replace any <…> placeholders with your own values first.
The tools search_files, read_file, list_files, and export_document should appear in the client's tool list; running list_files and getting Drive files back confirms the OAuth credentials are configured.
Once connected, you can ask your AI assistant things like:
No matching tools
Listed from the project's documentation, not tested by this site.
This community-maintained server uses OAuth to access Google Drive. It supports full-text search and reading Google Docs and Sheets content so cloud documents can be used as conversational context.
Comprehensive access to Google Search Console via MCP, with advanced analytics and quick win detection.
A production-ready MCP server that connects AI assistants to your Nextcloud instance.
Use your reMarkable tablet as a second brain for AI assistants. Read documents, browse files, extract text, and OCR handwriting.
An MCP server for interacting with Microsoft 365 and Office services through the Graph API.
Source revision 9be4674d1ddf Data synced 2026-10-14 Read the FMRS scoring method