"author:pipeworx-io" matching MCP servers:

Enables AI agents to scrape JavaScript-rendered web pages, extract structured JSON data using LLM prompts, and crawl websites with configurable page limits.

Enables AI agents to perform web searches using the Brave Search engine, providing an independent alternative to Google/Bing.

Enables AI agents to perform neural/semantic web search that finds pages by meaning, retrieve clean parsed page text from URLs or result IDs, and discover pages similar to a given URL. Runs either as a hosted gateway endpoint or a local stdio server, with optional plain-English routing across a broader data catalog.

Enables fetching and rendering web pages via ScrapingBee, extracting structured data with AI, and scraping Google search results through MCP.

Enables web scraping via the Decodo API, providing AI agents with access to data extraction through the Pipeworx MCP gateway.

Enables scraping web pages through ScraperAPI's rotating proxies, with options for markdown output, JavaScript rendering, geotargeting, and premium proxies, as well as structured Amazon product/search and Google search results.

Converts HTML to plain text, extracts hyperlinks, and pulls page metadata (title, description, Open Graph tags) from HTML content.

Wraps Scrapingdog, a proxy-based web scraping service, enabling AI agents to scrape web pages through a simple MCP interface.

Enables running Apify Actors for web scraping and automation, fetching dataset results, and scraping URLs to clean markdown via MCP.

Enables fetching web pages, extracting structured data with AI, and capturing screenshots via the Zyte API.

Enables scraping web pages through ScrapingAnt, returning raw HTML, LLM-ready Markdown, or structured JSON extracted from page content.

Enables analyzing a domain's sitemap structure, returning URL counts by path prefix and metrics like top-prefix share to distinguish normal sites from content farms.

Enables detecting what a website is built with—such as ecommerce platforms, CMSs, JS frameworks, analytics, and CDNs—by reading the page itself, returning evidence for each detection and listing detection coverage.

Enables users to browse curated technology feeds and fetch any RSS/Atom/RDF feed.

Enables fetching HTTP status cat images and browsing available status codes with descriptions and image URLs via http.cat.

Enables headless-Chromium web automation, including rendering fully-executed HTML, extracting structured data with CSS selectors, capturing screenshots, and AI-assisted smart scraping of web pages.

Enables AI agents to crawl web pages using the Crawlbase Crawling API via MCP, supporting plain English queries through Pipeworx gateway.

Enables independent web search over a non-commercial, non-SEO index that favors text-heavy, ad-light pages, useful for niche technical and historical topics.

Enables AI agents to perform LLM-optimized web searches, retrieve recent news articles with full text, and extract clean readable content from URLs. It returns synthesized answers, ranked cited sources, and page text suitable for grounding RAG workflows.

Converts RSS/Atom feeds to JSON via a single tool, enabling fetch of feed data as structured JSON through MCP.

Enables AI agents to browse and read curated software-development feeds, fetch any RSS/Atom/RDF feed via URL, and filter items by keywords.

Enables browsing and fetching transport and mobility news feeds from curated sources and arbitrary RSS/Atom/RDF URLs.

Web scraping and search MCP server that wraps Firecrawl API for URL discovery and web search with optional content retrieval.

Jina AI Reader/Search MCP that turns any URL into clean LLM-ready markdown and provides web search.

Enables interaction with the Microlink API for link previews and data extraction, requiring no authentication. It is part of the Pipeworx MCP gateway, providing access to over 673 live data sources.

Enables AI agents to access Bright Data's Web Unlocker and SERP API for scraping and search results, integrated through Pipeworx's MCP gateway.