Google Drive MCP
MCP server for managing Google Drive documents from Cursor, enabling file operations like list, search, download, upload, update, create folders, and delete.
README
Google Drive MCP
Servidor MCP en Python para gestionar documentos de Google Drive (cuenta Gmail / Google Workspace) desde Cursor.
Tools
| Tool | Descripción |
|---|---|
list_files |
Lista archivos/carpetas (raíz o por folder_id) |
search_files |
Busca por nombre en todo Drive |
get_file_info |
Metadatos y enlace web |
download_file |
Descarga texto o exporta Docs/Sheets/Slides |
upload_text_file |
Sube un archivo de texto |
update_text_file |
Actualiza contenido de un archivo |
create_folder |
Crea una carpeta |
delete_file |
Mueve a la papelera |
Permiso por defecto: lectura y escritura (drive). Para solo lectura, cambia el scope en src/drive_mcp/auth.py a drive.readonly y elimina el token.json para volver a autorizar.
1. Google Cloud
- Abre Google Cloud Console.
- Crea un proyecto (o usa uno existente).
- Activa Google Drive API (APIs & Services → Library).
- Configura la pantalla de consentimiento OAuth (External o Internal).
- Crea credenciales: APIs & Services → Credentials → Create credentials → OAuth client ID.
- Application type: Desktop app
- Descarga el JSON y guárdalo en la raíz del proyecto como
credentials.json.
Si la app está en modo Testing, añade tu Gmail en Test users.
2. Instalación
cd MCP-PROJECT
python -m venv .venv
source .venv/bin/activate
pip install -e .
3. Primer login (opcional, recomendado)
python -c "from drive_mcp.auth import get_credentials; get_credentials()"
Se abre el navegador, autorizas con tu Gmail y se crea token.json.
4. Cursor (mcp.json)
{
"mcpServers": {
"google-drive": {
"command": "/home/vpinto/Documents/Cooper/Repo2/MCP-PROJECT/.venv/bin/python",
"args": ["-m", "drive_mcp.server"],
"cwd": "/home/vpinto/Documents/Cooper/Repo2/MCP-PROJECT",
"env": {
"GOOGLE_CREDENTIALS_PATH": "/home/vpinto/Documents/Cooper/Repo2/MCP-PROJECT/credentials.json",
"GOOGLE_TOKEN_PATH": "/home/vpinto/Documents/Cooper/Repo2/MCP-PROJECT/token.json"
}
}
}
}
Ajusta las rutas si tu proyecto está en otra ubicación.
Variables de entorno
| Variable | Descripción |
|---|---|
GOOGLE_CREDENTIALS_PATH |
Ruta a credentials.json (OAuth client) |
GOOGLE_TOKEN_PATH |
Ruta donde se guarda token.json |
Notas
credentials.jsonytoken.jsonno se suben a git.- La descarga por MCP está limitada a ~2 MiB y a contenido texto (o export de Docs).
- El borrado envía a papelera; no elimina de forma permanente.
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.