Connect Claude to S3-compatible storage

Read one bucket on any S3-compatible object store - Hetzner, Cloudflare R2, MinIO, Wasabi or AWS - by listing its objects and reading small JSON files. Toolspoke puts 2 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: Access keys
Actions exposed: 2
What a call bills: Nothing
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install S3-compatible storage
Open the marketplace in your workspace, add S3-compatible storage to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with access keys. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. S3-compatible storage shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What S3-compatible storage asks for

Access keys. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

Endpoint URLRequired: The store's S3 endpoint, without the bucket. Hetzner is https://<location>.your-objectstorage.com; R2 is https://<account>.r2.cloudflarestorage.com.; https://nbg1.your-objectstorage.com
BucketRequired: The one bucket this install may read. Calls are path-style, so the bucket is the first path segment.; my-backups
Access keyRequired: Access key ID
Secret keyRequired: Secret access key
Signing regionOptional: The region the signature names. Most S3-compatible stores accept us-east-1; R2 wants auto.

What Claude can do in S3-compatible storage

2 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 2Reads
Writes: 0Writes
Destructive: 0Destructive

Reads

Fetches data and changes nothing.

list_objects
List objects in the bucket, optionally under a prefix, up to 1000 per page. Returns objects (key, lastModified, size), prefixes (the directories a delimiter groups keys into), truncated, and nextContinuationToken when there is another page - pass it back as continuation_token. With delimiter "/" and a prefix ending in "/", list one directory level.
get_json_object
Read one JSON object from the bucket, such as a status marker or a manifest, and return it parsed. At most the first 256 KB is read, so a large object cannot be pulled through here.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 2 actions above are the whole of it. A call to any other name is refused before it reaches S3-compatible storage rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
It only reads: Every action here reads. Nothing this connector can do changes anything in S3-compatible storage.
It reaches no further than your credential: Toolspoke holds no access to S3-compatible storage of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from S3-compatible storage: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in S3-compatible storage. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around S3-compatible storage's own rate limits. A call that S3-compatible storage refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in S3-compatible storage?

2 named actions: 2 that only read. They include list_objects and get_json_object. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the S3-compatible storage connector need?

Access keys. The connector asks for endpoint url, bucket, access key and secret key, and optionally signing region. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the S3-compatible storage connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 2 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the S3-compatible storage connector not do?

The 2 actions above are the whole of it. A call to any other name is refused before it reaches S3-compatible storage rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Every action here reads. Nothing this connector can do changes anything in S3-compatible storage. Toolspoke holds no access to S3-compatible storage of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in S3-compatible storage. An agent has to ask. Toolspoke does not retry, queue or back off around S3-compatible storage's own rate limits. A call that S3-compatible storage refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches S3-compatible storage's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls S3-compatible storage?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and what the call cost in sandbox time and model tokens. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More infrastructure connectors

Browse all of them