A Model Context Protocol server for Scrapezy that enables AI models to extract structured data from websites.
-
extract_structured_data
- Extract structured data from a website- Takes URL and prompt as required parameters
- Returns structured data extracted from the website based on the prompt
- The prompt should clearly describe what data to extract from the website
npm install -g @scrapezy/mcp
There are two ways to provide your Scrapezy API key:
-
Environment Variable:
export SCRAPEZY_API_KEY=your_api_key npx @scrapezy/mcp
-
Command-line Argument:
npx @scrapezy/mcp --api-key=your_api_key
To use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"scrapezy": {
"command": "npx @scrapezy/mcp --api-key=your_api_key"
}
}
}
You can use this tool in Claude with prompts like:
Please extract product information from this page: https://example.com/product
Extract the product name, price, description, and available colors.
Claude will use the MCP server to extract the requested structured data from the website.
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
npm run inspector
The Inspector will provide a URL to access debugging tools in your browser.
MIT