Connect Amazon S3 to Claude Code

Make Claude upload, organize, and manage objects in Amazon S3. From the terminal, inside the sessions where you already work.

Build my connector Talk to us

How do you connect Amazon S3 to Claude Code?

Claude Code reaches outside tools through MCP servers. To connect Amazon S3, you add a Amazon S3 MCP server: a small hosted service that exposes Amazon S3'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 Amazon S3 account. No API keys pasted into config files.

claude mcp add --transport http aws-s3 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 Amazon S3 once connected?

Full read-write S3 access lets Claude upload an object to a specific bucket and prefix, copy or move objects between locations, set object tags and metadata, generate presigned URLs, and delete objects once you approve. The bucket housekeeping that used to mean the console or CLI happens through the assistant.

Upload an object to a specific bucket and key prefix
Copy or move objects between buckets or prefixes
Set or update object tags and metadata for lifecycle and cost tracking
Generate a presigned URL for a single object after you approve it
Delete an object or a scoped set of objects once you confirm
List a prefix and propose a batched reorganization for review

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 Amazon S3 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 Amazon S3 API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Amazon S3 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 Amazon S3 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 Amazon S3 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 Amazon S3 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 Amazon S3'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 Amazon S3?

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 Amazon S3 account it signs in with. Revoking access is one click in Amazon S3.

More on the Amazon S3 connector

Amazon S3 connector for claude.ai Egnyte + Claude Code Google Cloud Storage + Claude Code Azure Blob Storage + Claude Code

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.

Build my connector Talk to us