MCP App Store
by KeenEthics
BucketDesk icon

BucketDesk MCP Server for Claude and ChatGPT

By BucketDesk

Overview

BucketDesk is a file workspace for the Amazon S3 buckets a business already owns. This connector lets Claude work with the files in the buckets your BucketDesk workspace has connected. Ask in plain language and Claude can: list your bucket connections and browse folders; search file names across every connected bucket; read text files such as Markdown, CSV and JSON; get file details and photo or video metadata; answer questions about PDFs and Office documents using the AI model in your own AWS account; share a file with one person by email; and list, unpack or zip archives. Claude never receives AWS keys. You sign in to BucketDesk with OAuth, and every call goes through the same permissions, bucket scopes and audit log as the BucketDesk app. Read-only tools are marked as such; sharing, document questions and archive jobs ask before they run. The connector cannot delete, upload or move files. Requires a BucketDesk Ultra workspace, signing in as a workspace admin.

How to connect

  1. Claude: Open the BucketDesk listing in the Claude connectors directory and choose Connect. Claude listing BucketDesk exposes 10 tools here.
  2. ChatGPT: Open the BucketDesk listing in the ChatGPT app directory and choose Connect. ChatGPT listing BucketDesk exposes 10 tools here.

Tools

ask-document

ChatGPT
Asks a question about one document (PDF, Word, text and similar) using the connection's own AI model in the customer's AWS account. Returns the answer with citations and a chat_id; pass chat_id with a follow-up question to keep the context. Costs AI usage and needs a write token.

browse

ChatGPT
Lists one page of folders and files in a bucket scope. Pass the returned next cursor to get the next page. starts_with finds names beginning with some text inside the folder.

fetch

ChatGPT
Gets one file by an id from search: its text for text formats (txt, md, csv, json, code and similar, up to 1 MB) and its details. For PDFs and Office files, use ask-document.

get-archive-job

ChatGPT
Gets an archive job's status and results. A finished compress job includes a download link that works for ten minutes.

get-media-metadata

ChatGPT
Gets when, where (latitude and longitude) and on what camera a photo or video was taken, plus its dimensions and video length, read from the file's own EXIF or QuickTime data.

get-metadata

ChatGPT
Gets one file's details: size, type, last modified, storage class, whether it must be restored first, and its etag.

list-connections

ChatGPT
Lists the workspace's storage connections (AWS accounts) and the bucket scopes in each. Other tools take a connection id and a scope id from here.

start-archive-job

ChatGPT
Starts an archive job: "inspect" lists what is inside a .zip, "extract" unpacks it into the bucket, "compress" zips a folder for download. Returns the job; check it with get-archive-job. Needs a write token.

ask-document

Claude

browse

Claude

fetch

Claude

get-archive-job

Claude

get-media-metadata

Claude

get-metadata

Claude

list-connections

Claude

start-archive-job

Claude

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/bucketdesk"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/bucketdesk)