Fetch a URL and return its main content as Markdown, text, or structured JSON for reading search results. Handles headings, links, language, truncation, and JavaScript-rendered pages.
MIT
744,618 tools. Updated 2026-11-04 23:54
"A tool for searching the web and returning page content as markdown" matching MCP tools:
- List futures prop firms and their plans from AlgoLift's open rules dataset, including plan IDs, account sizes, sale status, and verified-rule counts before searching the web.MIT
- 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
- Start multi-page web crawling to extract structured data with AI or convert content to markdown from a starting URL.MIT
- Read the active browser tab as markdown, plain text, cleaned HTML, or links; target elements with CSS selectors or extract only main content from the page.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
Matching MCP Servers
- FlicenseNot gradedqualityDmaintenanceFetches web pages and converts them to clean, readable markdown format by extracting main content while removing navigation, ads, and other non-essential elements to minimize token usage.4-
- AlicenseAqualityAmaintenanceEnables coding agents to add a bounded semantic-judgment layer for routing, ranking, extraction, verification, and escalation, returning typed signals and review recommendations.71Apache 2.0
Matching MCP Connectors
Create, edit, preview, publish, and manage web pages from MCP-capable AI clients.
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).
- Fetch any webpage’s full content as markdown, HTML, PDF, or screenshot, using automatic JavaScript rendering and proxies to handle protected or dynamic pages.MIT
- Retrieve a complete wiki page by slug, returning markdown body and structured payload. Use after listing pages to get the full page content.Apache 2.0
- 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
- Retrieve the extracted content of a completed asynchronous scrape job, including markdown, HTML, links, images, screenshot, and metadata; call only after scrape_status shows done.Apache 2.0
- 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
- Load a public URL in a full browser session so JavaScript runs and the DOM renders, then reuse a proxy exit for protected pages. Ideal for single-page apps, lazy-loaded content, and browser challenges.MIT
- Convert webpages into clean, formatted markdown for extracting content from documentation, articles, and web pages. Fetches any webpage and transforms HTML content into readable markdown format.MIT
- Parse HTML web pages and return clean markdown as JSON for articles, docs, wiki, and blog posts.MIT
- Retrieves the complete markdown content of a Capawesome documentation or blog page using its URL, providing full code samples and configuration details missing from search snippets.MIT
- Retrieve URL content as readable markdown with title and metadata, supporting site-specific extraction, PDF text, raw mode, and pagination.MIT
- Read Mockzilla documentation by topic or category, returning full markdown and public page URLs for the requested content.MIT
- Exports a Milanote board as Markdown, plain text, Word, PDF or PNG, returning text content for text formats and a temporary download URL for files.PolyForm Noncommercial 1.0.0
- Read a stored memory by ID or layer-prefixed path to retrieve its Markdown content, metadata, and supersession links; use search first when the ID is unknown.MIT