Search and fetch public web pages, or run Firecrawl search, scrape, and crawl to retrieve ranked results, readable content, or crawl job pages.
Apache 2.0
Destructive
741,183 tools. Updated 2026-11-04 01:59
"A tool for fetching and retrieving web pages or web content" matching MCP tools:
- Capture a screenshot of any web page by providing URL, width, and height. Optionally set a wait time to allow content or animations to load before capturing.Apache 2.0
- Check whether an uploaded web package finished ingesting by providing its ID. Poll until state becomes READY or detect ERROR.Apache 2.0
- Perform AI-powered web searches to extract structured data from search results for research, competitive analysis, and multi-source information gathering.MIT
- Start multi-page web crawling to extract structured data with AI or convert content to markdown from a starting URL.MIT
- Retrieve raw HTML from anti-bot or JavaScript-heavy websites. Fully renders the page using Web Unblocker or Chromium to bypass blocks and execute JavaScript.MIT
Matching MCP Servers
- AlicenseAqualityBmaintenanceEnables lightweight web search discovery and on-demand extraction of cleaned page text from supplied URLs, returning snippets, headings, links, and saved full text for longer pages.2BSD 3-Clause
- AlicenseAqualityCmaintenanceA Model Context Protocol server that provides real-time web search capabilities to AI assistants through pluggable search providers, currently integrated with the Brave Search API.532 npm16MIT
Matching MCP Connectors
26 tools: web pages to Markdown, metadata, tech stack, SSL, SEO, domains, email auth and SSO checks.
26 tools for AI agents: read any web page as clean Markdown, get metadata, structure and tech stack, and check redirects, SSL, security headers, robots.txt, sitemaps, feeds, WHOIS/DNS, SEO, broken links, email authentication (SPF, DMARC, DKIM) and SSO (SAML, OIDC), plus cron, regex, color, Unicode, time zone utilities and Hyperliquid market data. Hosted on Apify; authenticate with an Apify API token (Bearer). Pay per successful call ($0.001-$0.003).
- Search the web to retrieve full page content for factual lookups and specific questions. Optionally get AI-synthesized answers or filter by news and recency.MIT
- Search the web in six categories and auto-render top results to get both the search results and full page content in one round trip.MIT
- Read web pages as clean markdown, including multiple URLs or top N items from a listing, even when blocked, JavaScript-rendered, or behind a login.MIT
- Do not guess what the API supports. Discover features, endpoints, versions, content limits, and interpretation boundaries before choosing a content tool.MIT
- Discover news, academic papers, and GitHub issues by performing web searches. Obtain ranked results, links, and full page content for complex research tasks.MIT
- Scrape a public URL to create a searchable knowledge base. Extracts content from web pages (including JavaScript-rendered), chunks it, and indexes for RAG.MIT
- Soft-delete a web package. Refuses deletion while a live lesson uses it, preventing broken content.Apache 2.0Destructive
- Render any URL in a real browser to get markdown, HTML, screenshots, PDF, links, images, and structured data. Extract tables, metadata, or custom schemas from web pages.MIT
- Fetch 1-5 public web page URLs as Markdown in a single batch call. Returns each page's text, title, and final URL, plus per-page errors for any that fail.MIT
- Screenshot a web page in a headless browser and measure named elements, returning a PNG, exact rects and a spec stub for annotating web UIs.AGPL 3.0
- Read web-fetch compliance policy for allowed purposes, robots.txt/PII settings, acceptance requirements, and character caps before fetching or after a refused fetch.MIT
- Converts raw HTML into clean, boilerplate-free Markdown with preserved links and headings for LLM context ingestion; use it to replace cluttered web pages with readable article text.MIT
- Extract primary article body, bylines, publication timestamps, and reading time from web pages while stripping navigation, ads, and cookie banners.MIT
- Fetch public web pages and return clean Markdown of the main content without menus, ads, cookie banners, or footers, with metadata and a citation for reading, quoting, or summarizing pages.MIT
- Read one or more web pages by URL and return clean, LLM-ready markdown or text, handling hard sites with advanced mode.MIT