mcp-server-drive
A read-only Google Drive MCP server that allows searching files, reading file content (with auto-export for Google Docs, Sheets, Slides), and retrieving file metadata via OAuth authentication.
README
mcp-server-drive
A Google Drive MCP server. Runs locally as a subprocess of any MCP client (Claude Code, etc.), authenticates the user with their own Google account via OAuth, and exposes three read-only tools.
Tools
| Tool | What it does |
|---|---|
search_files |
Run a Drive query string (name = '…' and mimeType = '…' and trashed = false). Returns id, name, mimeType, parents, modifiedTime. |
read_file_content |
Fetch a file's content. Google Docs auto-export to text/markdown, Sheets to text/csv, Slides to text/plain. Override with mime_type. Non-native files come back via alt=media. |
get_file_metadata |
Full Drive metadata for a file: name, mimeType, parents, modified/created time, size, owners, webViewLink. |
Scope: https://www.googleapis.com/auth/drive.readonly. The server never writes to Drive.
Setup
-
Register an OAuth client in Google Cloud Console:
- Create a project (or reuse one).
- Enable the Google Drive API.
- APIs & Services → Credentials → Create credentials → OAuth client ID → Application type: Desktop app.
- Click Download JSON.
-
Save the downloaded file as
~/mcp-server-drive-tokens.jsonon every machine that will run the server. The server reads Google's JSON as-is and accepts the three shapes Google produces:{installed: {...}}(Desktop apps),{web: {...}}(Web apps), or a flat{client_id, client_secret, ...}blob.
The file holds the OAuth client credentials (one per Cloud project, shared across users of that client). It is NOT the per-user refresh token — that's written separately after the consent flow; paths below.
Install
npx -y @move32/mcp-server-drive
Or wire it into a plugin's .mcp.json:
{
"mcpServers": {
"gdrive": {
"command": "npx",
"args": ["-y", "@move32/mcp-server-drive"]
}
}
}
On first tool call, a browser tab opens for Google's consent screen. The user signs in with their personal Google account, grants read access, and the server stores the refresh token. Subsequent calls reuse the token silently. Access-token refresh is automatic.
Development
npm install
npm run lint # ESLint 9 flat config, zero warnings
npm run format:check # Prettier
npm run typecheck # tsc --noEmit
npm test # Vitest unit tests
npm run test:coverage # with v8 coverage
npm run build # emit to dist/
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.