Log inSubmit server
Screenshot Scout logo

Screenshot Scout

Capture HTTP and HTTPS webpages as images or PDFs with configurable browser, viewport, timing, and output options.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Screenshot Scout

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "screenshot-scout": {
      "command": "npx",
      "args": [
        "-y",
        "@screenshotscout/mcp"
      ],
      "env": {
        "SCREENSHOTSCOUT_ACCESS_KEY": "YOUR_VALUE_HERE",
        "SCREENSHOTSCOUT_SECRET_KEY": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Automated check passed— started and listed 1 tools correctly (5d ago).

Overview

Screenshot Scout MCP server connects MCP clients to Screenshot Scout for capturing HTTP and HTTPS webpages as images or PDFs. Its single `capture_screenshot` tool supports full-page and element captures, device and viewport settings, page interactions, content blocking, timing controls, caching, and PDF layout options. Results can include temporary URLs, structured metadata, or eligible image content embedded in the MCP response. Use it when an agent needs a rendered webpage snapshot, printable PDF, or controlled capture of a page region.

Use cases

  • Capture a webpage as a full-page PNG
  • Generate a formatted PDF from an online report
  • Render a selected page element for visual review
  • Block ads and cookie banners before capturing
  • Return a temporary URL instead of image bytes

Key features

  • Image and PDF webpage capture
  • Full-page and element screenshots
  • Device, viewport, country, and color-scheme controls
  • Page interaction and content-blocking options
  • Caching and temporary result URLs
  • Local stdio, Docker, MCPB, and hosted HTTP deployment

Tools1

What Screenshot Scout lets your agent do. Expand a tool for its parameters.

Verified live~1.1k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

20/21 checks healthy over the last 91d

What it can do

From the 1 tool this server returned when we ran it; 1 declare their own safety hints.

Makes network requests · 1Read-only tools · 1
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceNot published
Package age98 days
Maintainers1

Observed 2026-11-03 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 3d ago via OSV.dev · @screenshotscout/mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads536Package downloads in the last 30 days.
Last commit8d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed1Callable tools this server registers over MCP.

How Screenshot Scout works

What Screenshot Scout MCP server does

Screenshot Scout MCP server lets an MCP client request rendered captures from Screenshot Scout. The target can be any HTTP or HTTPS webpage that Screenshot Scout can load. The capture_screenshot tool produces image formats including PNG, JPEG, WebP, GIF, and TIFF, as well as PDF output.

Only the target url is mandatory. Captures can cover the complete page or focus on a selected element. The tool also supports viewport and device choices, country selection, light or dark color schemes, cookie-banner and ad blocking, chat-widget blocking, CSS selector hiding, and selector-based clicks before capture.

How it works

Each request sends the target URL and selected capture settings to Screenshot Scout, which loads the page and returns the requested result. By default, the capture uses a 1280×720 viewport, JPEG output, and quality 60. Timing can be adjusted with a page readiness condition, an additional delay, navigation timeout, and overall timeout.

The resultMode setting controls delivery. auto allows eligible PNG, JPEG, WebP, or GIF images to be included as MCP image content. url_only suppresses image bytes and returns a temporary result URL instead. TIFF is URL-only, and PDF bytes are not embedded; PDF responses can include structured metadata and a resource link when a result URL is available. Metadata may report the format, MIME type, dimensions, cache status, URL expiry, and the reason an image was not embedded.

Setup and configuration

A Screenshot Scout account and access key are required. Local npm/stdio use requires Node.js 22 or newer. A typical client configuration runs the package through npx and supplies SCREENSHOTSCOUT_ACCESS_KEY as a process environment value. Add SCREENSHOTSCOUT_SECRET_KEY only when the selected access key requires signed requests.

The server can also be built from a source checkout with npm ci and npm run build, then started with Node against the resulting dist/stdio.js. Docker can run the compiled stdio server with standard input attached and credentials passed through the environment.

Claude Desktop can install an MCPB extension downloaded from a GitHub release. A hosted Streamable HTTP endpoint is available at https://mcp.screenshotscout.com/mcp/api-key; clients using it must send the access key as a static Authorization: Bearer header. The hosted endpoint accepts only access keys and cannot be used with keys that require request signatures.

Tools and capabilities

  • Capture full webpages or selected elements.
  • Return PNG, JPEG, WebP, GIF, TIFF, or PDF results.
  • Set device, viewport dimensions, country, and color scheme.
  • Wait for page states, add delays, and configure navigation and capture timeouts.
  • Hide cookie banners, ads, chat widgets, or selected page elements; click selected elements.
  • Resize images, set JPEG/WebP quality, and configure PDF paper size, orientation, margins, backgrounds, scale, and page ranges.
  • Use caching with a configurable time-to-live and request temporary result URLs.

Limitations and notes

Captures consume the Screenshot Scout account's plan quota and rate limits. The target webpage and returned content should be treated as external and untrusted. Do not capture pages without authorization or place credentials in prompts, URLs, tool arguments, logs, or issue reports.

Result URLs are temporary and should be handled as sensitive links until their reported expiry. Inline image delivery is subject to format, dimensions, raw-size, and serialized-response limits. Images cannot exceed 8,192 pixels for requested dimensions, and the product of both requested image dimensions cannot exceed 64,000,000 pixels. PDF captures always cover the whole page, so image sizing, selector, and fullPage settings do not apply to PDF output.

The local stdio server adds no telemetry. Hosted-service application logging is limited to request method, response status, duration, and sanitized unexpected errors.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Screenshot Scout

Screenshot Scout is an MCP server that connects MCP clients to Screenshot Scout's webpage capture API. Its main tool, `capture_screenshot`, captures HTTP or HTTPS pages as images or PDFs, with controls for full-page or element output, viewport and device settings, page preparation, timing, caching, and result delivery.

Install it locally through `npx` with Node.js 22 or newer, or use the hosted Streamable HTTP endpoint. Local setup requires a Screenshot Scout access key; Claude Desktop can also install the MCPB extension from a GitHub release, and Docker can run a locally built stdio image.

Yes, Screenshot Scout works with Cursor through its local stdio configuration. Configure Cursor to run the npm package and provide `SCREENSHOTSCOUT_ACCESS_KEY` in the environment; add the secret key only when the access key requires signed requests.

Yes, `capture_screenshot` can create PDFs with selectable paper formats, landscape orientation, printed backgrounds, margins, scaling, and page ranges. PDF captures always contain the whole page, and PDF bytes are returned through a resource link or temporary URL rather than embedded in the MCP response.

Related MCP servers

All in Browser Automation All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewScreenshot Scout AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/screenshot-scout?style=directory)](https://allmcps.com/mcp/screenshot-scout)
HTML Embed
<a href="https://allmcps.com/mcp/screenshot-scout"><img src="https://allmcps.com/api/badge/screenshot-scout?style=directory" alt="Screenshot Scout on AllMCPs" /></a>