Renders a screenshot of a website and returns it as an image
ScreenshotOne MCP provides a simple way to capture high-quality screenshots of any website directly through your AI assistant. This integration leverages the ScreenshotOne API service to render websites and return images that can be analyzed or used in your workflows. With this MCP, you can easily visualize web content, capture specific elements, and generate visual references without leaving your AI assistant interface. It's particularly useful for web testing, content analysis, and creating visual documentation.
ScreenshotOne MCP Server allows you to capture screenshots of websites directly through your AI assistant. This integration connects to the ScreenshotOne API service, which specializes in high-quality website rendering and screenshot capture.
Before using this MCP, you'll need:
git clone https://github.com/screenshotone/mcp.git
cd mcp
npm install && npm run build
To use this MCP with Claude for Desktop, add the following configuration to your Claude Desktop config file located at ~/Library/Application Support/Claude/claude_desktop_config.json
:
{
"mcpServers": {
"screenshotone": {
"command": "node",
"args": ["path/to/screenshotone/mcp/build/index.js"],
"env": {
"SCREENSHOTONE_API_KEY": "your_api_key_here"
}
}
}
}
Replace path/to/screenshotone/mcp/build/index.js
with the actual path to the built index.js file and your_api_key_here
with your ScreenshotOne API key.
You can also run the MCP server standalone:
SCREENSHOTONE_API_KEY=your_api_key_here node build/index.js
Once configured, you can ask your AI assistant to capture screenshots using natural language:
The assistant will use the render-website-screenshot
tool to capture and display the requested website.
Your ScreenshotOne API key is sensitive information. When configuring the MCP:
If you encounter issues: