How to Connect an S3 Bucket to Gemini

S3 bucket in Gemini

Short answer: add the bucket to AnythingMCP as a File Search connector with a key that can only list and read it. AnythingMCP indexes the full text of the documents under the prefix you pick and keeps the index in sync. Then connect AnythingMCP to Gemini CLI. Gemini can find files by name and by content, read the pages it needs and give you the file itself, attached or as a temporary download link. Nothing is ever written to the bucket.

An AI assistant cannot open an S3 bucket on its own, and one that could would have to download every file to answer one question. The index is what makes a question like "what does article NT-601 cost in the current price list?" take seconds.

What you need

• The endpoint: empty for Amazon S3, for example https://fra1.digitaloceanspaces.com for DigitalOcean Spaces, or the URL of your MinIO.
• The region and the bucket name.
• An access key that can only list and read this bucket.
• An AnythingMCP workspace: AnythingMCP Cloud (7 days free) or your own self-hosted install.

S3 has no real folders: the "folders" you see in the wizard are key prefixes, and the one you pick limits what is indexed. Amazon S3, DigitalOcean Spaces, MinIO, Wasabi, Hetzner Object Storage and Backblaze B2 all work.

Set it up

Step 1 — Set up the File Search connector

In AnythingMCP, open the Marketplace and pick S3 bucket (File Search), or open Connectors → New → File Search and choose S3. A short wizard guides you; there is no long form to fill in.

1. Connect. Enter the endpoint (empty for Amazon S3), the region, the bucket, the access key and its secret, and the prefix to use, for example invoices/.
2. Test. AnythingMCP connects, signs in and lists the folder before anything is saved, and shows a checklist (address, reachability, encryption, server identity, login, folder) with what to fix when a step fails.
3. Scan. Click Scan folder. AnythingMCP lists the folder without indexing it yet and shows a tree with the number of files in every subfolder, the file types and the years. Folders that look like archives (Alt, Old, Archive, Backup) are already unticked, so Gemini never quotes an outdated document. A bar compares your selection with your plan while you tick folders, file types or an age limit; when the selection is larger than the plan, untick more or upgrade.
4. Describe. AnythingMCP drafts the connector's description from the scan, for example "Archived supplier invoices and delivery notes, PDF, 2023–2026". This text tells Gemini what the folder contains and when to search it. If an AI model is configured on the server, the wizard can draft it with AI and says exactly what is sent (folder names, file names, the first 2,000 characters of up to 20 sample files, personal data masked); otherwise the draft is built from the folder structure. Edit it as you like.
5. Activate. Choose the tool prefix, the sync interval and the MCP servers that get the connector, and click Activate.

The first sync starts right away and runs in a separate background service: Gemini and your other connectors keep answering at full speed while it runs. The connector's Files tab shows its progress: files found, indexed and skipped, the last and next sync, and a Sync now button.

Step 2 — Copy the server URL

In MCP Servers, open the server you chose in the wizard and copy its URL.

Step 3 — Add the connector in Gemini

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Gemini CLI reads MCP servers from ~/.gemini/settings.json (on Windows %USERPROFILE%\.gemini\settings.json). Add:

{
  "mcpServers": {
    "anythingmcp": {
      "httpUrl": "https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID",
      "headers": { "X-API-Key": "YOUR_MCP_API_KEY" }
    }
  }
}

1. Create an MCP API key in AnythingMCP under MCP Servers → your server → API keys, and paste it in place of YOUR_MCP_API_KEY.
2. Save the file and restart gemini.
3. Run /mcp inside Gemini CLI (or gemini mcp list in your shell): anythingmcp should show as connected.
4. Start prompting: Gemini CLI can now call the file search tools.

Step 4 — Ask

Start a new chat and ask about the content of your files. Gemini searches the index first, opens the pages that matched and answers with the file name, the page and the file's date, so you can check the source.

What Gemini can do with the files

<prefix> is the tool prefix you choose in the wizard, for example pricelists. Every tool except _share_file only reads.

Supported files: text is extracted from over 100 file types: PDF (page by page); Word, Excel and PowerPoint including macro and template variants and .xlsb; OpenDocument; Outlook .msg, .eml and .mbox with the text of their attachments; .rtf, .epub, .xps; Apple Pages, Numbers and Keynote (through their PDF preview); .svg and the text of .dxf CAD drawings; CSV, Markdown, HTML, XML, JSON, YAML, calendars and contacts; and source code. Every other file is still found by name, and PDF pages and images can be shown to the AI as pictures. Scanned PDFs without a text layer are read with OCR on Enterprise.

Prompts to try in Gemini

• "Search the invoices prefix for all invoices from Nordtor in 2025 and add up the totals."
• "Find the delivery note for order 4711-200 and tell me what was delivered."
• "Which documents in the bucket mention the Kessler framework agreement?"
• "Give me the PDF of the newest monthly report as a download link."

How syncing works

Every object carries an ETag. AnythingMCP compares it with the last run and downloads only new and changed objects. Files whose content is identical to the indexed version are recognised by their checksum (SHA-256) and not processed again. Deleted files leave the index. A file that cannot be read is retried on the next syncs and, after three failures (at once for password-protected files), stays findable by name, with the reason on the Files tab.

Syncing runs in its own background service, separate from the server that answers Gemini: a large first sync does not slow down your questions, and search keeps working with the last index while a sync runs.

When the folder outgrows your plan, the sync pauses before downloading anything instead of indexing only part of it: the Files tab shows how many files the folder now holds against your plan, Gemini keeps searching the files already indexed and is told that newer files may be missing, and you can untick folders or upgrade. A paused folder is checked again once a day and resumes by itself when it fits.

Security

• Read-only. The connector only lists and reads. It has no tool that writes, renames or deletes on the bucket.
• Your workspace only. The index is stored per workspace and every query is limited to it, by the application and again by the database (Row-Level Security).
• Credentials are stored encrypted and decrypted only in the background sync service. Gemini and your colleagues never see them.
• Who sees what follows your MCP roles: a role without the file tools does not see them. On Enterprise you can also allow or deny folders per role.
• File content is data. The tools tell the model never to follow instructions found inside a file.
• A key for one bucket. Give AnythingMCP a key that can only list and read this bucket, not your account's main key.
• AnythingMCP Cloud connects only to servers on the public internet: a host in a private network is refused, also after a redirect. A server in your office network must be reachable from outside, or you run AnythingMCP self-hosted next to it.

Limits by plan

Self-hosted: Starter includes one File Search connector with up to 500 files, Team three connectors with 2,000 files, Enterprise has no limit and syncs down to every 5 minutes; the largest file is set by FILES_MAX_FILE_BYTES (100 MB by default). Self-hosted File Search needs a paid licence or the 30-day trial, which has the Team limits; the free Community edition has no File Search after the trial. All plans.

FAQ

Where does Gemini CLI look for MCP servers? In ~/.gemini/settings.json for your user, or in .gemini/settings.json inside a project. gemini mcp list shows each server and whether it connects.

Does it work with DigitalOcean Spaces, MinIO or Wasabi? Yes. Enter the provider's endpoint, for example https://fra1.digitaloceanspaces.com for Spaces or the URL of your MinIO; leave it empty for Amazon S3.

What permissions does the key need? Listing and reading this bucket, nothing else. The connector never writes to the bucket.

Can AnythingMCP Cloud reach a MinIO in our office network? No. On the Cloud the endpoint must be on the public internet. Run AnythingMCP self-hosted next to a private MinIO.

Does AnythingMCP copy all of the bucket? No. AnythingMCP keeps the extracted text, not the files. A file is read again only when it changed, or when you ask for the file itself.

Is vector search used? No. Company documents are searched for exact names, codes and numbers, where keyword search with page-level results is more reliable than embeddings.

Related

• Search your company file server with AI
• Find prices in supplier price lists with AI
• Search inside Nextcloud and WebDAV files with AI
• Share files from an AI chat as download links
• Connect an S3 Bucket to Claude
• Connect an S3 Bucket to ChatGPT
• Connect an S3 Bucket to Microsoft Copilot
• Connect an S3 Bucket to Cursor
• Connect an S3 Bucket to Muse
• Other file sources in Gemini: SFTP server, FTP / FTPS server, WebDAV server, Nextcloud, ownCloud, Synology NAS, QNAP NAS, Fritz!Box storage, Hetzner Storage Box, Network folder (self-hosted)