Scrapezy
OfficialThe Scrapezy MCP Server enables AI models to extract structured data from websites by providing a URL and a customizable prompt. With this server, you can:
Extract structured data from web pages (like product names, prices, descriptions)
Specify exactly what data to extract through clear, detailed prompts
Integrate with Claude Desktop and other AI models via the Model Context Protocol
Use the MCP Inspector for debugging communication between the server and AI models
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Scrapezy extract product details from https://amazon.com/dp/B08N5WRWNW"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@scrapezy/mcp MCP Server
A Model Context Protocol server for Scrapezy that enables AI models to extract structured data from websites.
Features
Tools
extract_structured_data- Extract structured data from a websiteTakes 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
Related MCP server: spider-cloud-mcp
Installation
Installing via Smithery
To install Scrapezy MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @Scrapezy/mcp --client claudeManual Installation
npm install -g @scrapezy/mcpUsage
API Key Setup
There are two ways to provide your Scrapezy API key:
Environment Variable:
export SCRAPEZY_API_KEY=your_api_key npx @scrapezy/mcpCommand-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"
}
}
}Example Usage in Claude
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.
Debugging
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 inspectorThe Inspector will provide a URL to access debugging tools in your browser.
License
MIT
Available Tools
1 toolextract-structured-dataC
Extract structured data from a website.
Inputs: prompt (required), url (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined as extracting structured data from websites, leaving no room for confusion.
The single tool name follows a clear verb_noun pattern ('extract-structured-data'), and since there are no other tools, consistency is inherently perfect with no deviations or mixed conventions.
One tool is too few for a server named 'Scrapezy', which suggests a scraping or data extraction domain. A single tool limits functionality and feels thin, as typical scraping tasks might require multiple operations like listing URLs or handling different data formats.
The tool surface is severely incomplete for a scraping domain. It only provides extraction, with obvious gaps such as no tools for discovering URLs, navigating pages, handling authentication, or managing scraping sessions, which will likely cause agent failures in real-world scenarios.
Maintenance
Related MCP Connectors
Web scraping MCP server — scrape, extract structured data, screenshot any site with anti-bot bypass.
One MCP server for all web data. Scrape, search, crawl, and AI research in one install.
One MCP server for 180+ live web-data APIs returning clean JSON from sites that block scrapers.
Web scraping, browser automation, screenshots and AI data extraction for AI agents via MCP.
Related MCP Servers
- FlicenseBqualityDmaintenanceAn MCP Server for Web scraping and Crawling, built using Crawl4AI224-
- AlicenseBqualityCmaintenanceMCP server for the Spider web crawling and scraping API, enabling AI agents to crawl, scrape, search, and extract web data.132MIT
- AlicenseAqualityCmaintenanceMCP server providing tools for web scraping, browser automation, computer vision, audio transcription, and RAG via API.9258 PyPIMIT
- AlicenseAqualityDmaintenanceMCP server that exposes Scrapingdog APIs for web scraping, search engine queries, social media profiles/posts, screenshots, and datacenter proxy usage via nine tools.911 npm1MIT