Skip to content
Custom Connectors

Connect Google Cloud Storage to Claude Code

Let Claude upload, move, and manage objects in Google Cloud Storage. From the terminal, inside the sessions where you already work.

How do you connect Google Cloud Storage to Claude Code?

Claude Code reaches outside tools through MCP servers. To connect Google Cloud Storage, you add a Google Cloud Storage MCP server: a small hosted service that exposes Google Cloud Storage's data and actions over the Model Context Protocol. With a custom connector we build for you, that is one command in the terminal, then an OAuth sign-in with your own Google Cloud Storage account. No API keys pasted into config files.

claude mcp add --transport http google-cloud-storage https://your-connector-url/mcp

Then run /mcp inside a Claude Code session to sign in. Add it with --scope project and the connector is checked into the repo for your whole team.

What can Claude Code do in Google Cloud Storage once connected?

Full read-write Google Cloud Storage access lets Claude list and read objects, upload new ones, copy or move between buckets, set or remove object metadata, and manage lifecycle and access settings within your permissions. The bucket housekeeping and transfers that used to mean console clicks or gsutil commands happen where the data already lives.

  • Upload a file or generated artifact to a specific bucket and prefix
  • Copy or move objects between buckets or folders
  • List objects under a prefix and report sizes, classes, and last-modified dates
  • Set or remove custom metadata and content types on objects
  • Delete or archive objects after you approve the action
  • Apply or update a lifecycle rule on a bucket

One connector, every Claude surface

The connector we build is a remote MCP server, which is the same standard claude.ai and Claude Desktop use. Add it once and the same Google Cloud Storage access works in Claude Code for you, in claude.ai for the rest of the team, and in Claude Desktop. One build, one set of permissions, one monthly plan covering all of them.

Build it yourself, or have it built?

If you live in the terminal, you can absolutely write your own MCP server against the Google Cloud Storage API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Google Cloud Storage changes its API and when the MCP spec itself moves, and scoping write actions so an agent can never do more than you intended. We build Google Cloud Storage connectors with separated read and write tools and approval gates on destructive actions, then host and maintain them so they keep working while you work.

Frequently asked questions

Does the same Google Cloud Storage connector work in claude.ai and Claude Code?
Yes. It is one remote MCP server. Claude Code adds it with a single "claude mcp add" command; claude.ai and Claude Desktop add it as a custom connector in Settings. Each person signs in with their own Google Cloud Storage account, so access always matches what that person can already see and do.
Do I need to host or maintain anything myself?
No. The connector runs as a hosted service we operate: we handle uptime, token health, API changes on Google Cloud Storage's side, and MCP spec migrations under the monthly plan. Your side is one command in the terminal and an OAuth sign-in.
Is it safe to give a coding agent write access to Google Cloud Storage?
Write access is scoped, not blanket. Read tools and write tools are separated, destructive actions like deleting or sending are gated behind your explicit approval, and the connector can never exceed the permissions of the Google Cloud Storage account it signs in with. Revoking access is one click in Google Cloud Storage.

Tell us what you run. We'll build the connector.

Pick your tool, choose what Claude should do, and get an instant scope and price. No call required.