MCP tool reference · #531 of 563 by publishers
read_url
Exposed by 9 servers from 8 publishers, read from the live servers by the Serverdex check; most of them sit in Search & Web; 100% of them take a url parameter; the most-starred is Skill Audit — Security Scanner for MCP Servers & Agent Skills (5 stars).
read_url(url: string, …)Parameters
share = % of the 9 servers whose schema has it · required = % of those that mark it required| Parameter | Type | Share | Required | Usual description |
|---|---|---|---|---|
| url | string | 100% | 100% | Page to fetch |
| format | string | 22.2% | 0% | Requested output format from this tool's enum; it does not name a file or cause a local file write. |
| maxChars | integer | 22.2% | 0% | Maximum Markdown characters to return, 100-200,000 (default 50000). Longer content is cut and truncated is set to true. |
| _apiKey | string | 11.1% | 0% | Your Jina API key. Required, Jina no longer serves anonymous requests. Pipeworx injects its own when one is configured; free keys at https://jina.ai/reader. |
| engine | string | 11.1% | 0% | Как забирать страницу: auto (по умолчанию - начинает с быстрого способа и сам поднимается, если текста не оказалось), fast (быстро, для статики и документации), |
| fresh | boolean | 11.1% | 0% | Прочитать страницу заново, не беря недавно прочитанный текст. Нужно, когда страница только что изменилась. На цену не влияет: кредит списывается в любом случае. |
| max_chars | integer | 11.1% | 0% | Maximum Markdown length to return. |
| offset | integer | 11.1% | 0% | С какого символа продолжить чтение. Берите значение из предыдущего ответа этого тула («продолжить: offset N»), не считайте сами. Пусто - с начала страницы. / Wh |
Source: the input schema each server returns for read_url, aggregated over the 9 index-tier servers; type and description are the values most servers use. Rebuilt every 6 hours.
Servers with read_url
9 of 9 · 8 publishers · 9 answering live · most-starred first, 3 per publisher| # | Server | Publisher | Category | ★ | Live | How it describes read_url |
|---|---|---|---|---|---|---|
| 1 | Skill Audit — Security Scanner for MCP Servers & Agent Skillseltociear · AI & Agents | eltociear | AI & Agents | 5 | yes | Fetch a URL and return its main content as clean Markdown, boilerplate stripped. (Free. This server also sells a paid API — call `paid_catalogue` for the routes and prices; x402 over USDC on Base, no signup.) |
| 2 | TokenGuard — Real-World Data Tools for Agentseltociear · Search & Web | eltociear | Search & Web | 1 | yes | Fetch a URL and return its main content as clean Markdown, boilerplate stripped. (Free. This server also sells a paid API — call `paid_catalogue` for the routes and prices; x402 over USDC on Base, no signup.) |
| 3 | EUCompliance Tools - Invoice Guard & Agent Evidencepatrickpi1312 · Finance | patrickpi1312 | Finance | — | yes | Fetch a public web page as clean Markdown or text while refusing internal and private addresses, suitable for reading evidence before an agent acts on a link. |
| 4 | Jina Readerpipeworx-io · Search & Web | pipeworx-io | Search & Web | — | yes | Fetch any web page as clean, LLM-ready markdown (strips nav/ads), ideal for giving an agent the readable content of a URL. |
| 5 | срезAI — MCP-сервер и поисковый API для ИИ-агентовsrezai-team · Search & Web | srezai-team | Search & Web | — | yes | Открывает одну страницу по известному адресу и возвращает её текст чистым markdown - без навигации, рекламы, скриптов и HTML. JavaScript выполняется на нашей стороне, поэтому SPA тоже читаются. Когда: адрес известен и нужен текст - статья, документация, карточка товара. Когда не: адреса нет - сначала web_search; страниц несколько - read_urls (один вызов вместо пяти); нужны 2-5 конкретных полей - |
| 6 | Clearcrawlclearcrawl · Documents & Knowledge | clearcrawl | Documents & Knowledge | — | yes | Fetch a URL and return clean markdown plus structured JSON (title, author, links, tables). Cost: 2 credits ($0.002). |
| 7 | agent-web — URL to LLM-ready markdown: a polite, robots-respecting web page reader (free)foomworks · Search & Web | foomworks | Search & Web | — | yes | Fetch one publicly reachable URL and return clean, LLM-ready markdown (title + page description + word count + markdown). HTML pages are extracted to markdown — including HTML tables, which become GitHub-flavored Markdown tables; URLs pointing straight at a Markdown or plain-text document (raw READMEs, llms.txt, docs) are passed through verbatim. Polite by design: honors the origin's robots.txt fo |
| 8 | Stormapboriskendev · Developer Tools | boriskendev | Developer Tools | — | yes | Read a web page for an AI: fetch a public page and return its main content as clean, LLM-ready Markdown (navigation, footers, scripts and cookie banners removed) plus metadata: title, description, author, published/modified dates, canonical URL, language and word count. Reads server-rendered HTML (no JavaScript execution) and respects robots.txt. |
| 9 | WebReadagentgate-builder · Search & Web | agentgate-builder | Search & Web | — | yes | Fetches one public web page and returns its main content as clean Markdown (navigation, scripts, ads and boilerplate removed; links made absolute) plus title and metadata. Use it whenever your agent needs to read, quote or summarize a page. Respects robots.txt, refuses private/internal hosts and non-default ports, follows redirects, and handles HTML, plain text and Markdown (no JavaScript renderin |
Stars from GitHub as stored in the Serverdex index (re-read every 7 days per server); live = answered the last daily check of its hosted endpoint.