Scrapezy — Claude Code MCP server for website data extraction
Scrapezy extracts structured data from a webpage using its URL and a description of the fields to find. Use it when an agent needs specific details gathered from a site.
no license updated 2026-10-29
Open on GitHubWhat Scrapezy does
The MCP server provides extract_structured_data. It takes a page URL and instructions describing the information to collect, then returns the extracted data in a structured form. Clear field requirements help the agent target the right details.
Scrapezy requires an API key. Provide it through SCRAPEZY_API_KEY or the --api-key argument; without the key, the server cannot access Scrapezy. Install the package with npm install -g @scrapezy/mcp. For debugging, run the MCP Inspector with npm run inspector.
What it helps with
- extract product names and prices from a page
- collect a product description and its available colors
- retrieve website details based on specified fields
Example prompts for the agent
- Gather the product details on this webpage and return them as structured data.
- Find the company name, address, and contact phone number on this site.
How to install Scrapezy
Install
The MCP registry has no launch command for it: see the repository README
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Scrapezy
How do I install Scrapezy in Claude Code?
Install the package with npm install -g @scrapezy/mcp. Scrapezy also needs an API key, supplied through SCRAPEZY_API_KEY or the --api-key argument.
What does Scrapezy do?
This MCP server retrieves structured information from webpages. It takes a URL and a description of the data to find.
What does Scrapezy need to run?
It requires a Scrapezy API key. Set SCRAPEZY_API_KEY or pass the key with --api-key.