Installation
Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).
claude mcp add --transport http google-drive 'https://gateway.pipeworx.io/google_drive/mcp'{
"mcpServers": {
"google-drive": {
"type": "http",
"url": "https://gateway.pipeworx.io/google_drive/mcp"
}
}
}@pipeworx/mcp-google_driveclaude mcp add google-drive -e 'PIPEWORX_API_KEY=<your pipeworx_api_key>' -- npx -y @pipeworx/mcp-google_drive@0.2.0{
"mcpServers": {
"google-drive": {
"command": "npx",
"args": [
"-y",
"@pipeworx/mcp-google_drive@0.2.0"
],
"env": {
"PIPEWORX_API_KEY": "<your pipeworx_api_key>"
}
}
}
}Variables d'environnement
PIPEWORX_API_KEYsecret Optional Pipeworx API key. Without it calls are anonymous and capped daily; a free key raises the cap.
Documentation
Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.
Sommaire
mcp-google_drive
Google Drive MCP Pack
Part of Pipeworx — an MCP gateway connecting AI agents to 1683+ live data sources.
Tools
| Tool | Description |
|---|---|
drive_list_files | List files in your Google Drive. Optionally filter by name, type, owner, or modified date (e.g., 'name contains "report"'). Returns file names, IDs, types, and metadata. |
drive_get_file | Get metadata for a specific Drive file by ID. Returns name, type, size, owners, permissions, creation date, and last modified time. |
drive_get_content | Download file content from Drive. Export Google Docs/Sheets/Slides to PDF, Word, Excel, etc., or retrieve raw content from other files. |
drive_create_file | Create a new file in Drive with specified name, content, and type (e.g., 'text/plain', 'application/pdf'). Returns the file ID for future reference. |
drive_search | Search Drive files by name, type, owner, modified date, or full text using query operators (e.g., 'name contains "report"', 'mimeType = application/pdf'). Returns matching files and IDs. |
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"google_drive": {
"url": "https://gateway.pipeworx.io/google_drive/mcp"
}
}
}What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/google_drive/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}Both URLs reach the same gateway and the same 1683+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
No MCP client? Call it over HTTP
This pack runs against a connected google_drive account, so it needs a Pipeworx key: sign in at https://pipeworx.io/account, connect google_drive, then call POST https://gateway.pipeworx.io/v1/tools/drive_list_files with Authorization: Bearer <your Pipeworx key>. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/drive_list_files. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
Standalone (no gateway account)
This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:
{
"mcpServers": {
"google_drive": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-google_drive"]
}
}
}Or run it directly to confirm it starts:
npx -y @pipeworx/mcp-google_driveIt speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call
for only this pack's tools — none of the shared meta-tools the gateway
connection above adds. Same source, same tools, no ask_pipeworx routing.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Google_drive data" })The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Questions fréquentes
Qu'est-ce que Google_drive ?
Google Drive MCP Pack
Comment installer Google_drive ?
Il fonctionne comme serveur distant. Dans Claude Code : claude mcp add --transport http google-drive 'https://gateway.pipeworx.io/google_drive/mcp'. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.
Faut-il une clé API pour Google_drive ?
Oui. Il attend PIPEWORX_API_KEY, à renseigner dans sa configuration.
Google_drive est-il open source ?
Oui. Son code est sur GitHub sous licence MIT.
Qui maintient Google_drive ?
Il est publié par pipeworx-io. AI.tn le référence sans le maintenir ni le recommander.
Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.