Website Content MCP
未认领MCP server exposing website content in agent-readable structured form
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'website-content-mcp' -- 'npx' '-y' '-p' '@sarutobi-sasuke/website-content-mcp' 'website-content-stdio'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
6 个工具中显示 6 个
文档中列出的工具 (6)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
content_get_page
Fetch a page URL, strip to clean markdown, return content + metadata, content hash and any schema.org Product/Offer facts. Supports maxlength; forced refresh is disabled on public HTTP by default.
content_get_sitemap
Return the raw sitemap structure (URLs + last-modified/priority/change-frequency when present).
content_health
Server status: configured site, allowed hosts, cache directory, cache size, last fetch time.
content_list_pages
List discoverable pages (sitemap → robots.txt sitemaps → configured list). Returns URL, title, last-modified when known.
content_refresh
Walk the discoverable pages and warm the cache so contentsearch has something to search. Skips robots-disallowed pages. Available on stdio; opt-in on HTTP.
content_search
Keyword search over already-fetched/cached pages. Returns URL, score, snippet.