What is Scraperis Mcp

scraperis-mcp is an MCP Server designed for Scraper.is, enabling users to scrape data from any website using natural language prompts through the Scraper.is API.

Use cases

Use cases for scraperis-mcp include retrieving product listings from e-commerce sites, gathering user reviews, extracting article titles and authors from news websites, and collecting job postings from job boards.

How to use

To use scraperis-mcp, install it via Smithery with the command ‘npx -y @smithery/cli install @scraperis/scraperis-mcp --client claude’, and configure it in your Claude Desktop settings.

Key features

Key features include natural language scraping, which allows users to extract data using plain English, smart data parsing that returns structured JSON data or clean Markdown, and support for complex queries such as filtering by price and ratings.

Where to use

scraperis-mcp can be used in various fields including e-commerce, data analysis, market research, and content aggregation, where data extraction from websites is required.

MCP Server for Scraper.is

The scraper tool is an asynchronous utility that leverages the Scraper.is API to fetch and process content from websites using natural language prompts. This tool is designed to handle various scraping scenarios efficiently, allowing you to specify exactly what data you want to extract in plain English.

Key Features

1. Natural Language Scraping

   • Extract data from websites using plain English prompts
   • Automatically identifies URLs and extraction requirements from your prompts
   • Supports complex queries like filtering by price, ratings, dates, etc.

2. Smart Data Parsing

   • Returns structured data in JSON format when specific data points are requested
   • If parsing is disabled, converts the content into clean, readable Markdown
   • Handles various data types: text, numbers, dates, prices, etc.

Examples on how to query Claude or other LLM

• “Get me the top 10 products from producthunt.com”
• “Find all products under $50 with 4+ star ratings on amazon.com/deals”
• “Extract all article titles and authors from techcrunch.com/ai”
• “Get the latest job postings from ycombinator.com/jobs”
• “Collect user reviews from the first 3 pages of trustpilot.com/company/apple”

Prerequisites

Install uv first.

https://docs.astral.sh/uv/getting-started/installation/#installation-methods

Setup Instructions

Installing via Smithery

To install Scraper.is MCP server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @scraperis/scraperis-mcp --client claude

Setup with Claude Desktop

Local/Dev Setup Instructions

Clone repo

git clone <git:url>

Install dependencies

Install MCP server dependencies:

cd mcp-server-scraperis

# Create virtual environment and activate it
uv venv

source .venv/bin/activate # MacOS/Linux
# OR
.venv/Scripts/activate # Windows

# Install dependencies
uv sync

Setup with Claude Desktop

Debugging

Run:

make run

Then access MCP Inspector at http://localhost:5173. You may need to add your API key in the environment variables in the inspector under SCRAPERIS_API_KEY.

Rate Limits and Credits

• Each successful scraping operation consumes 1 credit
• Operations will fail if the user has insufficient credits
• Users can check their credit balance in the dashboard
• Credits can be added through the account page (/dashboard/account)

License

This project is licensed under the MIT License.

About Scraper.is

Scraper.is is a powerful web scraping API service that provides reliable and efficient data extraction capabilities for businesses and developers. With features like automatic proxy rotation, JavaScript rendering, and intelligent parsing, it helps you collect the data you need from any website.