MCP Server

The ScreenshotRun MCP Server lets AI agents — like Claude, Cursor, or Windsurf — take screenshots, extract page metadata, and check API usage autonomously. Instead of writing code, you just tell the AI "take a screenshot of example.com" and it does the rest.

MCP (Model Context Protocol) is an open standard for connecting AI models to external tools. By adding the ScreenshotRun MCP server, your AI assistant gets three tools: capturing screenshots with full API parameter support, extracting page metadata, and monitoring usage quota.

Available Tools

The MCP server exposes three tools to the AI agent:

Installation

The MCP server is distributed as an npm package: screenshotrun-mcp. No global installation needed — it runs via npx.

Claude Desktop

Add this to your Claude Desktop config file (claude_desktop_config.json):

{
  "mcpServers": {
    "screenshotrun": {
      "command": "npx",
      "args": ["-y", "screenshotrun-mcp"],
      "env": {
        "SCREENSHOTRUN_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Config file location:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

Restart Claude Desktop after saving the config.

Claude Code (CLI)

claude mcp add screenshotrun npx -y screenshotrun-mcp \
  -e SCREENSHOTRUN_API_KEY=YOUR_API_KEY

Cursor

Create or edit .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "screenshotrun": {
      "command": "npx",
      "args": ["-y", "screenshotrun-mcp"],
      "env": {
        "SCREENSHOTRUN_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Windsurf

Add to your Windsurf MCP configuration:

{
  "mcpServers": {
    "screenshotrun": {
      "command": "npx",
      "args": ["-y", "screenshotrun-mcp"],
      "env": {
        "SCREENSHOTRUN_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

take_screenshot Parameters

The take_screenshot tool accepts all ScreenshotRun API parameters. The AI agent picks the right ones based on your natural language request.

Source (one required)

Output

Viewport & Device

Appearance

Blocking

Interaction

Injection

Timing

Clipping & Resizing

Advanced

Geolocation

PDF Options (format=pdf)

Scroll Video

extract_content Parameters

The extract_content tool extracts page metadata without downloading the full screenshot image. It returns structured data that the AI agent can use for SEO analysis, content audits, or building link previews.

Returns:

• Title — page title from <title> tag
• Description — meta description
• Open Graph — og:title, og:description, og:image, og:type, og:url, og:site_name
• Twitter Card — twitter:card, twitter:title, twitter:description, twitter:image, twitter:site
• Favicon URL
• HTTP status code

Usage Examples

Once the MCP server is connected, you can ask the AI to capture screenshots using natural language. Here are some examples of what you can say:

Basic screenshot

Take a screenshot of https://example.com

Mobile screenshot in dark mode

Capture https://example.com as it looks on a mobile phone in dark mode

Full-page screenshot

Take a full-page screenshot of https://example.com/pricing in WebP format

Render HTML to image

Render this HTML as an image: <h1>Hello World</h1><p>This is a test</p>

Screenshot with stealth mode

Take a screenshot of cloudflare.com using stealth mode to bypass bot detection

Geo-targeted screenshot

Capture google.com as seen from Tokyo, Japan

Extract page metadata

Extract the OG tags and meta description from competitor.com

Click and capture

Click the "Show More" button on example.com/products, then take a screenshot

Visual comparison

Take screenshots of stripe.com, paddle.com, and lemonsqueezy.com. Compare their pricing page designs.

Check remaining quota

How many screenshots do I have left this month?

How It Works Under the Hood

1. The AI decides to use the take_screenshot or extract_content tool based on your request.
2. The MCP server sends a capture request to the ScreenshotRun API.
3. It polls for completion (every 2 seconds, up to 60 seconds timeout).
4. Once ready, the image is downloaded and returned to the AI as base64 data (or metadata is returned as structured JSON for extract_content).
5. The AI can then analyze the image, compare it with others, or save it to disk.

Security

• Your API key is stored in the MCP config file and passed as an environment variable. It is never sent to the AI model itself.
• The MCP server only communicates with api.screenshotrun.com — no data is sent elsewhere.
• Each screenshot captured by the AI agent counts toward your plan quota, just like any other API request.

Source Code

The MCP server is open source: github.com/webmox/screenshotrun-mcp — npm package