工具 API
apify--web-fetch
This tool calls the Actor "apify/web-fetch" and retrieves its output results. Use this tool instead of the "call-actor" if user requests this specific Actor. Actor description: Download any web page by URL and convert it to clean Markdown, plain text, HTML, and other formats. Automatically renders JavaScript and works around bot blocking. The Actor provides a real-time API for quick response times. Use this tool to fetch a specific http(s) URL and return its complete content (one URL per call; http and https only). It renders JavaScript and bypasses anti-bot protection, so it also retrieves pages where a plain HTTP fetch gets blocked, fails with an error such as 403 or 429, or returns incomplete content. The page comes back verbatim - full content, no summarization - as Markdown, plain text, HTML, the raw response body, or the list of links on the page. Examples of when to use: - User provides a URL and wants its content, its data or links, or an answer that requires reading that page - A previous attempt to fetch a page was blocked, returned an error or CAPTCHA, or came back incomplete because the page needs JavaScript rendering - Verbatim page content is needed, e.g. for quoting, extraction, or archiving This tool does not search the web - it needs a URL. To find pages by query, use a web search tool instead. If the exact URL cannot be fetched (e.g. a non-http(s) scheme), say so rather than silently substituting a different URL.
调用信息
- 工具标识
- apify-mcp-server.apify--web-fetch
- 服务提供方
- Apify
- 平均响应
- 0 ms
- 近 7 天调用
- 0
输入参数
url必填**REQUIRED** The URL to fetch. Only `http://` and `https://` schemes are supported; others are rejected. Example values: "https://apify.com" http(s) URLs only - for any other scheme (e.g. ftp:), tell the user this tool cannot fetch it rather than substituting a different URL.
formatsThe Actor converts the fetched content to the requested format(s). A format that doesn't apply to the content type returns `null`; if none of the requested formats apply, the run fails. The Input form is prefilled with `markdown`; clear it to auto-select `markdown` for HTML/PDF, `text` for text-based content, or `raw` for images, archives, and other binary content. Example values: ["markdown"]
headersCustom HTTP headers to send to the target URL, as an object of header names and values, e.g. `{ "Accept-Language": "fr-FR", "Authorization": "Bearer TARGET_SITE_TOKEN" }`.
waitSecsMax seconds (0–45, default 30) to cap the wait for the Actor run to reach terminal state. For long-running Actors the response returns at the cap with the current run status; follow `nextStep` to poll via get-actor-run. Set to 0 to fire-and-forget.