Agents Index

URLpipe

Online

Read any page with its JavaScript run: Markdown, screenshots, metadata, console errors, Lighthouse.

Visit publisherConnectJSON

What it can do: 17 tools

  • list_projects read-onlyThe projects this token can reach, each with how many requests it has made in the last 30 days and where its results are delivered. Start here: every other tool takes a project_id from this list. A project is the unit a
  • get_usage read-onlyWhat the organization's plan allows, how much of it is left this period, and what each operation costs. Worth reading before a run of expensive calls: the operations differ by seventeen times in price, so the difference
  • fetch_markdownExposes POST /markdown. Renders the page in headless Chrome and converts its main content to clean Markdown — headings, lists, links and code kept, navigation, sidebars and cookie banners dropped. Start here when you wa
  • fetch_htmlExposes POST /html. Returns the page's HTML after JavaScript has run and redirects have been followed — the DOM a real browser sees, not the empty shell curl returns. 1 credit. Use it when you need the markup itself: a
  • capture_screenshotExposes POST /screenshot. Captures the whole rendered page as a PNG — JavaScript executed, web fonts and images included, exactly as a browser would draw it. 1 credit, whichever options you use. Use it to see a page rat
  • capture_pdfExposes POST /pdf. Prints the whole rendered page to a PDF — JavaScript executed, web fonts and lazy-loaded images included, its headings as bookmarks. 1 credit, whichever options you use. Use it to archive or hand on a
  • capture_console_errorsExposes POST /console. Loads the page in headless Chrome and returns what it reported through console.error and console.warn during load, plus uncaught exceptions and unhandled promise rejections (not console.log). 1 cre
  • run_lighthouse_auditExposes POST /lighthouse. Runs a real Google Lighthouse audit against the live page: performance, accessibility, best-practices and SEO scores plus Core Web Vitals. 2 credits — dearer than a page fetch because the audit
  • extract_metadataExposes POST /meta. Reads everything a page declares about itself — Open Graph, Twitter cards, meta tags, JSON-LD, microdata and links — into one object with the same keys on every page: title, description, site name, ki
  • detect_technologiesExposes POST /technologies. Detects what a page is built with — CMS, e-commerce platform, JavaScript frameworks and libraries, analytics and tag managers, advertising and marketing tools, CDN, web server, programming lan
  • extract_keywordsExposes POST /keywords. Returns the 5–15 terms and phrases that best represent the page, ordered by relevance — ranked by a language model, not by raw frequency. 15 credits. As with summarize_page: if you are going to r
  • summarize_pageExposes POST /summarize. Returns a concise Markdown summary of the page's main content, with the navigation, ads and boilerplate left out. The most expensive operation we sell, at 17 credits, because it runs a language
  • extract_dataExposes POST /extract. Reads the page and fills an object YOU define: pass `fields`, each with a name, a type and a description of what to take from the page, and get back exactly those keys in that order. Anything the p
  • scrape_urlExposes POST /scrape. Runs any subset of the other operations in one request, served from a single page visit where possible. Each operation is billed and stored exactly as the individual call would be, so this is not a
  • get_result read-onlyExposes GET /result/:token. Returns the result of a past request, in the same form the call that made it would have returned — Markdown as Markdown, a structured operation as its object, a screenshot as an image, a PDF a
  • list_requests read-onlyA project's recent requests, newest first, with each one's token. Look here before fetching a page: if somebody already pulled it, passing that token to get_result returns the same result for nothing. A /scrape appears
  • get_request read-onlyEverything about one past request except its result: what was asked for, how long each stage took, whether it came from the store, and how the webhook delivery went. This is the metadata; get_result returns the page its

Connect it

Claude Code
claude mcp add --transport http urlpipe https://urlpipe.dev/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://urlpipe.dev/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "urlpipe": {
      "url": "https://urlpipe.dev/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "urlpipe": {
      "type": "http",
      "url": "https://urlpipe.dev/mcp"
    }
  }
}

Questions

What does URLpipe do?

Read any page with its JavaScript run: Markdown, screenshots, metadata, console errors, Lighthouse. It exposes 17 tools to AI assistants.

What tools does URLpipe provide?

17 tools, including list_projects, get_usage, fetch_markdown, fetch_html, capture_screenshot, capture_pdf, capture_console_errors, run_lighthouse_audit, extract_metadata, detect_technologies, extract_keywords, summarize_page….

How do I connect URLpipe to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://urlpipe.dev/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does URLpipe require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is URLpipe online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes URLpipe?

urlpipe.dev. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Browser Automation