Crawlbase Codex 技能
通过 Crawlbase MCP 抓取页面并管理存储结果。
完整 Codex 插件技能包覆盖 HTML、Markdown、截图以及存储列表、计数、读取、删除和批量操作。
适用场景
- 将页面提取为 HTML 或 Markdown
- 捕获渲染页面截图
- 查看和管理已存抓取结果
使用方法
准备 Crawlbase 账号和静态或 JavaScript 页面需要的凭据，使用上游 Codex 插件连接 MCP，再提供网址或存储操作。
Skills
crawl-html
Crawl a URL and return its full raw HTML content. Supports JS rendering, custom user agents, device emulation, geo-targeting, and optional screenshot capture.
crawlbase/crawlbase-codex-plugincrawl-markdown
Crawl a URL and extract clean, readable Markdown content. Strips ads, navigation, and boilerplate — returns only the main content.
crawlbase/crawlbase-codex-plugincrawl-screenshot
Take a full-page or viewport screenshot of any URL. Supports desktop and mobile viewports, custom dimensions, and configurable page-load wait times.
crawlbase/crawlbase-codex-pluginstorage-bulk-delete
Delete up to 100 stored pages from Crawlbase Cloud Storage in one call. Irreversible.
crawlbase/crawlbase-codex-pluginstorage-bulk-get
Retrieve up to 100 stored pages from Crawlbase Cloud Storage in one call, optionally auto-deleting each item after retrieval.
crawlbase/crawlbase-codex-pluginstorage-count
Return the total number of documents in Crawlbase Cloud Storage for a token.
crawlbase/crawlbase-codex-pluginstorage-delete
Delete a single stored page from Crawlbase Cloud Storage by rid.
crawlbase/crawlbase-codex-pluginstorage-get
Retrieve a single previously-stored page from Crawlbase Cloud Storage by rid or url. Returns the stored body as JSON, HTML, or Markdown.
crawlbase/crawlbase-codex-pluginstorage-list
List rids currently in Crawlbase Cloud Storage, with scroll-based pagination (up to 1000 rids per call). Useful for enumerating everything stored under a token.
crawlbase/crawlbase-codex-plugin