MCP-сервер URLpipe

• Имя в реестреdev.urlpipe/mcpподтверждён в реестре MCP

Имя в реестре лежит в пространстве urlpipe.dev. Реестр пускает в такое пространство только того, кто доказал владение доменом через DNS или HTTP.

• Состояниеотвечаетпроверено 2026-10-20
• Инструменты17
• Сервер называет себяurlpipe
• Версия сервера1.4.0
• Версия протокола2025-06-18

2026-10-20 сервер ответил на initialize и tools/list без входа. Первый ответ за 209 мс.

• Инструменты делают все проверенные сценарии: Convert web pages to clean markdown for an AI agent; Capture full-page screenshots or PDFs of URLs; Check client websites for changes over time.
• Проверок пока 2 из 7, нужных, чтобы судить о надёжности.

Вывод сделан правилами по замерам выше. Вероятный первый вызов выбрала модель по списку инструментов: прочитайте описание, прежде чем на него полагаться.

• Оценка INITE MCPчерез неделюдля оценки нужно 7 ежедневных проверок, пока 2
• Что агент может с ним сделать3 из 3 сценариев
• Отвечалидёт замерпроверок пока 2, долю покажем после 7
• Медиана первого ответа705 мс
• Место в контексте агента≈ 13 350 токеновописания всех инструментов (17), агент держит их в контексте на каждом ходу
• Описания инструментовA · 100 из 100
• Типизированные ответы17 из 17 инструментовобъявлен outputSchema: ответ приходит с типами и читается сразу

• Все инструменты проходят все шесть проверок.

Программа проверяет сервер раз в день: initialize и tools/list, без модели. Токены - это длина описаний из расчёта примерно четыре символа на токен. Оценка - среднее шести проверок имени, описания, схемы и аннотаций каждого инструмента. Она говорит, насколько понятно описаны инструменты, а не о том, работают ли они. Оценка складывается только из замеренного: отвечает ли сервер (30%), делает ли работу продукта (25%), описания (20%), контекст (10%) и использование (15%). Незамеренная часть не учитывается, а скрытая инструкция ограничивает оценку 40 баллами. Состояние MCP-серверов вендоров: методика и цифры →

• list_projects

  The 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 request is billed…

• get_usage

  What 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 between…

• fetch_markdown

  Exposes 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 want to READ a page…

• fetch_html

  Exposes 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 specific attribute…

• capture_screenshot

  Exposes 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 rather than read it…

• capture_pdf

  Exposes 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 page as a…

• capture_console_errors

  Exposes 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 credit. What you…

• run_lighthouse_audit

  Exposes 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 runs in its own…

• extract_metadata

  Exposes 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, kind of page…

• detect_technologies

  Exposes 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 language, payment…

• extract_keywords

  Exposes 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 reason over the…

• summarize_page

  Exposes 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 model over the…

• extract_data

  Exposes 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 page does not give…

• scrape_url

  Exposes 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 discount — with…

• get_result

  Exposes 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 as an embedded…

• list_requests

  A 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 as one entry — its…

• get_request

  Everything 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 itself. Reach for this…