Snapstack

What is SnapStack?

SnapStack is a local browser extension and bundled MCP server that lets you capture any browser tab in one click and stack the screenshot locally. Your AI assistant can then read those screenshots on demand over the Model Context Protocol, without copy-pasting images. It is designed for users of MCP‑capable clients like Claude Code.

How to use SnapStack?

Install both the browser extension and the always‑on local server (both install in a couple of minutes). Click the extension to capture a tab; the screenshot is stacked on your local machine. Then ask your LLM to “look at my screenshots” and it picks them up via MCP.

Key features of SnapStack

• Capture any browser tab in one click.
• Stack screenshots locally on your own machine.
• AI reads stacked screenshots on demand via MCP.
• Works with any MCP‑capable client (e.g., Claude Code).
• 100% local – no uploads, no account, no telemetry.

Use cases of SnapStack

• Hand browser screenshots to your AI assistant without manual copy‑pasting.
• Let your LLM review multiple tab captures in a single conversation.
• Privacy‑friendly screenshot archiving for AI‑assisted analysis.

FAQ from SnapStack

How does SnapStack actually work?

A browser extension captures the current tab and sends the screenshot to a small local server running on 127.0.0.1. The server holds the stack and exposes it over MCP so your LLM can retrieve the images on demand.

Is SnapStack really 100% local?

Yes. Captures go only to the local server on your own machine. Nothing is uploaded to any external service, and there is no account or telemetry.

Do I need an account to use SnapStack?

No. SnapStack requires no account registration or login.

Which AI clients work with SnapStack?

Any MCP‑capable client, including Claude Code and others that support the Model Context Protocol.

Where are my screenshots stored?

On your own machine, in the stack managed by the local server (127.0.0.1). No data leaves your computer.