Skip to content
MCP server

CaptureKit

Website screenshots, PDF export, page content and AI analysis through one API

Pricing
Free trial
Platforms
API, CLI
Runs
Locally or Remotely
Version
0.1.0
Listing updated
3 days ago

About CaptureKit

CaptureKit is an MCP server for web search and scraping. It can run locally on your machine or as a hosted remote server.

CaptureKit renders pages in managed headless browsers and returns images or documents, so no Chrome pool is needed. The site lists PNG, JPEG, WebP and PDF output, full-page or CSS-selector capture, 17+ emulated devices, automatic blocking of cookie banners and ads, and an optional stealth mode with residential proxies.

The content side extracts metadata, links, clean Markdown or HTML, and an AI analysis returns a summary, value proposition, categories, use cases and optional contact signals. Edge caching with TTLs up to 30 days makes repeat requests resolve fast.

The MCP tools are capture, content, analyze, website_crawler, usage and an account-enabled stats. Use hosted mcp.capturekit.dev with an x-api-key header; sign-up gives 100 free credits.

Install

Run in a terminal

claude mcp add --transport http mcp https://mcp.capturekit.dev/

Add to Settings → Connectors → Add custom connector

https://mcp.capturekit.dev/
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.capturekit.dev/"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.capturekit.dev/"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp": {
      "serverUrl": "https://mcp.capturekit.dev/"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.capturekit.dev/"
    }
  }
}

Configuration

  • CAPTUREKIT_API_KEYCaptureKit API key.Required

Tools this server provides (6)

Taken from the project documentation; the running server may differ.

capture
Screenshot a page as PNG, JPEG, WebP or PDF.
content
Extract metadata, links, Markdown or HTML.
analyze
AI summary, categories and use cases for a page.
website_crawler
Fetch raw HTML without rendering.
usage
Usage and credit balance.
stats
Infrastructure health; enabled per account.

What it does

Screenshot and PDF
Capture full-page or selector shots in four formats.
Device emulation
Render as 17+ real devices.
Content extraction
Pull Markdown, HTML, metadata and links.
AI page analysis
Summaries, categories and contact signals.
Edge caching
Cache responses with TTLs up to 30 days.

Good for

  • Archive time-stamped legal or pricing pages
  • Generate social card thumbnails
  • Attach screenshots to bug reports
  • Feed clean page text to an LLM

Pricing

Free trial

100 free credits; paid plans, prices not published

Prices change. Check capturekit.dev before you buy.

CaptureKit FAQ

What formats can it capture?

PNG, JPEG, WebP and PDF.

How do I try it?

100 free credits, no card required.

Can it get past bot detection?

The site lists a stealth mode with residential proxies and fingerprint rotation.

Which tools are available?

capture, content, analyze, website_crawler, usage and stats.

Is CaptureKit free?

CaptureKit is a paid product with a free trial.

How do I add CaptureKit to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp https://mcp.capturekit.dev/

What are the best alternatives to CaptureKit?

The closest alternatives to CaptureKit are Browser Use, Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search and Oya Browser.

Alternatives to CaptureKit

  1. Browser Use

    MCP server

    Browser agents and cloud browsers for AI, with an MCP server for web tasks

    • 7 tools
    • Remote
    • Freemium
    • 121K GitHub stars
    • Browser automation
  2. MCP server for AI clients to scrape sites with HTTP and stealth browser sessions

    Runs locally
    • 17 tools
    • Open source
    • 104K GitHub stars
    • Web search and scraping
  3. MCP server that lets AI agents search, scrape and interact with web pages

    • 3 tools
    • Remote
    • Freemium
    • 7.8K GitHub stars
    • Web search and scraping
  4. SearXNG Search

    MCP server

    MCP server for web search and page reading through a SearXNG instance

    Runs locally
    • 3 tools
    • Open source
    • 1.4K GitHub stars
    • Web search and scraping
  5. Oya Browser

    MCP server

    HIPAA-oriented agentic browser with replayable playbooks, reachable over MCP

    • 32 tools
    • Remote
    • Freemium
    • 349 GitHub stars
    • Browser automation
  6. Mantis

    MCP server

    Browser MCP server that gives agents numbered text pages instead of screenshots

    Runs locally
    • 1 tool
    • Open source
    • 5 Hacker News points
    • Browser automation