Every cloud storage.
One app, no downloads.

Connect Local, HTTPS, S3, Drive, SFTP, WebDAV, Dropbox, Azure, OneDrive — plus B2, Wasabi, R2, GCS as one-click S3 presets. Preview tables and Parquet files inline — no full file pulls. Auto-profile any column. Run SQL on remote bytes. Pair machines into a private data network and query the whole network in plain English. Credentials in your OS keychain, files never on our servers.

Sery Link · File Preview

orders_2024.parquets3://analytics/orders/2024/

1.4 GB · 4,209,847 rows · 5 cols · Snappy compression·12 KB read · footer only·Resolved in 1.8s

5 columns

ColumnTypeNullsDistribution

order_idBIGINT0.0%4.2M unique · primary key

customer_idBIGINT0.0%2.1M unique · foreign key

amountDOUBLE0.2%$0.99 → $9,847.00 · avg $42.18

statusVARCHAR0.0%3 values · paid · pending · cancelled

created_atTIMESTAMP0.0%2024-01-01 → 2024-12-31 · partitioned

Bytes read this preview · 12 KB0 bytes uploaded · file stays in S3

Local

HTTPS

Drive

SFTP

WebDAV

Dropbox

Azure

OneDrive

Backblaze B2·preset

Wasabi·preset

Cloudflare R2·preset

GCS·preset

Every storage you have, in one Sources sidebar

Local folders, S3 buckets, Google Drive accounts, SFTP servers, WebDAV mounts, B2 buckets — all bookmarked in one app. Add a source in seconds. Browse, preview, profile, query — all from one catalog.

9 protocols + 4 S3 presets

Local, HTTPS, S3, Drive, SFTP, WebDAV, Dropbox, Azure, OneDrive — plus B2, Wasabi, R2, GCS as one-click S3 presets. One app replaces the handful of cloud-console + file-browser tabs you have open right now.

Preview without downloading

Click any Parquet on S3 → schema and sample rows in under two seconds via the Parquet footer. The 1.4GB file stays in S3. CSV / TSV / Excel preview streams just enough.

Credentials in your OS keychain

AWS keys, Drive OAuth tokens, SFTP passwords — all stored via your OS's native credential store. We never see them. Pre-flight tests them on save so a typo never persists.

Install on a second machine? It's a network now.

One workspace key pairs your machines. Search and AI chat span every machine AND every source they each connect to. Files never leave the storage they live in.

One workspace key

Create a workspace key on sery.ai, paste it into each machine's Connect dialog. The same key works on as many machines as you want.

Files stay put

Each machine indexes its own data locally. Only schemas and the final answers travel — raw files never leave the device where they live.

Unified answers

“Find my 2024 tax docs across my machines” returns a list with a machine-name column so you know which device has which file.

How it works

Three steps. The first two run entirely on your laptop. The third is optional and only happens if you explicitly connect to sery.ai.

Connect

Click + Add Source → pick your protocol → enter credentials. Sery pre-flights the connection (catches typos and region mismatches before persisting), stores the credential in your OS keychain, and registers the source as a bookmark in the sidebar.

—9 protocols: Local, HTTPS, S3, Drive, SFTP, WebDAV, Dropbox, Azure, OneDrive
—4 S3-compatible presets: B2, Wasabi, R2, GCS
—OS keychain credentials, never on our servers
—Pre-flight test catches bad creds on the modal

Preview & search

Click any tabular file → schema + sample rows render inline in <2s (Parquet footer over the wire; CSV streams just enough). Auto-profile shows null %, unique values, distributions. Search bar matches filenames + column names + document content across every connected source.

—Preview Parquet without downloading the full file
—Auto-profile (null %, unique, min/max/avg)
—Column-name search across every source
—Convert any tabular file to Parquet in place

Ask (optional)

Connect to sery.ai with a workspace key when you want natural-language queries — "total revenue last quarter across my spreadsheets." The agent runs server-side; SQL travels through a private tunnel to your machine; only result rows come back. Skip it forever and the gateway still works.

—Ask in plain English; get a direct answer
—Spans every connected source (and every paired machine)
—Files never leave their storage; only result rows travel
—Workspace sharing for up to 5 invited collaborators

Why the network matters

Sery's value compounds with every machine you add. One install is a desktop app. Two are a network. Five are a moat.

Free · universal data gateway

Sery Link, on every storage

• Connect every cloud storage you have
• Preview Parquet / tabular files without downloading
• Per-file column profiles (null %, unique, min/max/avg)
• Column-aware search across every connected source
• Format convert (CSV / TSV / XLSX → Parquet) in place
• Local MCP — Claude Desktop, Warp, Cursor, Continue
• Runs fully offline; no account required

Plus · AI + network

One network across machines

• Plain-English queries at app.sery.ai across every paired machine
• Cross-machine search and SQL fan-out
• Cross-machine MCP via mcp.sery.ai
• Workspace recipes shared across every machine
• Schema-change notifications fan out to every endpoint
• 5 invited collaborators on one bill (hub-and-spoke)

Sery's cloud is a coordination layer, not a storage layer. It coordinates — identity, catalog, routing, sharing — but never holds your file contents. The atoms (your files) stay in the storage that owns them. The network is what makes them queryable as one.

Plus plan

Use Sery from any AI tool you already love

Sery exposes your workspace catalog as an MCP endpoint at mcp.sery.ai. Drop your API key into Claude Desktop, Warp, Cursor, or Continue and your LLM gets nine read-only tools to browse, search, sample, and SQL-query every file in your workspace — without any of them leaving the machine that owns them.

~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "sery": {
      "url": "https://mcp.sery.ai/sse",
      "headers": {
        "Authorization": "Bearer sk_live_…"
      }
    }
  }
}

restart Claude Desktop 9 tools loaded

sery · 9 toolsconnected

list_folderenumerate pathscatalog

search_filesfuzzy matchcatalog

get_schemacolumns + typescatalog

sample_rowsfirst N rowscatalog

read_documentPDF/DOCX contentcatalog

query_sqlremote DuckDBquery

query_dataNL queryai

list_datasetsworkspace catalogai

get_dataset_schemadataset detailsai

SQL travels to your machine; only result rows return.

MCP setup runbook (Claude Desktop, Warp, Cursor, Continue)

Want a local-only MCP server that doesn't need a Sery account? Install cargo install sery-mcp and point it at any folder — same nine tools, fully on-device. See open source.

Ready to try all features?

Free forever with unlimited machines and the full local file-manager surface. $19/mo unlocks unlimited cloud AI — 7-day trial, no card required.

Get started free

Every cloud storage.One app, no downloads.