Search results
197 packages found
Sort by: Default
- Default
- Most downloaded this week
- Most downloaded this month
- Most dependents
- Recently published
A crawler and search engine for websites
A tool for extracting structured content from web pages with customizable selectors and crawling options
Model Context Protocol (MCP) integration for Scraper.is - A web scraping tool for AI assistants
Advanced web scraping framework built on Puppeteer designed to bypass rate limits with smart proxy rotation and browser fingerprinting protection
Package for Apify/Crawlee that allows to store encrypted text values into the Storages
一个基于 MCP 协议的网页内容获取工具,支持多种模式和格式,可与 Claude 等 AI 助手集成
A wrapper around cURL-impersonate, a binary which can be used to bypass TLS fingerprinting.
Google parser is a lightweight yet powerful HTTP client based Google Search Result scraper/parser with the purpose of sending browser-like requests out of the box. This is very essential in the web scraping industry to blend in with the website traffic.
- google-parser
- google-scraper
- google-search
- google-this
- scraper
- search-results
- search
- serp
- web-scraping
- @nrjdalal
Model Context Protocol (MCP) server for Firecrawl Simple - provides web scraping and crawling capabilities to LLMs
- mcp
- model-context-protocol
- firecrawl
- web-scraping
- crawling
- llm
- ai
- claude
- cursor
- sitemap
- web-crawler
- headless-browser
MCP server for extracting content from web pages
A wrapper around cURL-impersonate, a binary which can be used to bypass TLS fingerprinting.
Model Context Protocol (MCP) server for pure.md, the markdown delivery network for LLMs
- ai-search
- claude
- claude-desktop
- crawler
- cursor
- data-extraction
- markdown
- mcp
- mcp-server
- model-context-protocol
- pure.md
- puremd
- search-tools
- unblocker
- View more
MCP server for Firecrawl web scraping integration. Supports both cloud and self-hosted instances. Features include web scraping, batch processing, structured data extraction, and LLM-powered content analysis.
utility for web scraping and fetching the html from a url or using puppeteer to interact with the page. getHtml uses various strategies in a 'waterfall' approch to get the content of the url, depending on priorities, such as stealth, speed, freshness.
This is a minimal MCP (Multi-Command Protocol) server implementation for product search, designed to work seamlessly with Claude's tool integration. It uses `FastMCP` to expose a simple tool that allows language models to query an API for product listings
Nemo-webminer is a Node.js toolkit for scraping content from any website.
A Model Context Protocol (MCP) server for WaterCrawl, enabling AI systems to perform web crawling and search operations
Unofficial high performance API for SIGAA IFSC using web scraping.
A minimal TypeScript library for fetching and parsing Google Scholar pages.
DeepSearch MCP Server with Brave Search API and Puppeteer content extraction