Webskan

io.github.kamilobstawskiagent-ux由 GitHub 账号 kamilobstawskiagent-ux 发布v0.1.0更新于 Nov 7, 2026

Audit and re-check a live website: Lighthouse, SEO, accessibility, security, links, journeys.

已验证Streamable HTTP可网页运行网页搜索与抓取开发者工具安全与监控

概览

AI 生成的概览

Webskan 从外部审计公开上线的网站——Lighthouse、SEO、无障碍、安全头、链接与用户旅程——并在修复后重新检查。

可以做什么
  • 快速扫描单个页面，获取 Lighthouse 移动端评分、指标、HTTPS/TLS、安全响应头与页面 SEO 标签
  • 启动整站异步爬取，最多 30 个页面，覆盖失效链接、逐页 SEO、无障碍、安全与用户旅程
  • 查询审计状态，或读取按严重程度排序的发现项及其对应页面地址
  • 部署修复后重跑同一审计，获得已修复、仍存在、新增与未验证发现项的差异对比
适用场景
适合在部署网站改动后立即验证结果，或需要对公开网站做技术审计并形成“审计—修复—复查”闭环时使用。它只读，且只查看网站的公开版本。
运行要求
远程 MCP 端点，使用 streamable HTTP；免费方案无需账号或密钥。付费开发者方案可选在 Authorization 头中传入 Bearer 许可证密钥以提高额度。目标网站必须可公开访问，不支持 localhost、私有 IP、.local 以及需要登录的站点。
安装前请注意
免费方案有速率限制：单页扫描每 IP 每小时 10 次；整站审计每 IP 每 24 小时 2 次，且每个主机每 24 小时仅 1 次，对同一主机重复调用会返回已有审计。付费方案每月 29 美元，需在 Authorization 头中传入许可证密钥。审计为只读，但目标网址会发送给第三方服务，结果会被缓存并保留（扫描结果 7 天，审计结果 30 天）。Lighthouse 评分每次运行会有几分波动。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Webskan，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.kamilobstawskiagent-ux%2Fwebskan/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "webskan": {
      "type": "http",
      "url": "https://webskan.com/mcp"
    }
  }
}

README

Webskan plugin for Claude Code

Audit and re-check the website your agent just shipped. The plugin adds the Webskan remote MCP server (https://webskan.com/mcp) and a /webskan:site-check skill that teaches Claude Code the loop: audit, fix the high and medium findings by id, deploy, re-check, report fixed / still open / new.

What Webskan checks, from the outside, in a real mobile browser: Lighthouse (mobile and desktop), a crawl of up to 30 pages with SEO checks on each, axe-core accessibility (WCAG 2.1 AA), security headers and TLS, broken links, forms, the cookie banner, and customer journeys (404 page, menu, search, cart to checkout). Every finding has a stable id, so the re-check is an exact diff.

Install

In Claude Code:

/plugin marketplace add kamilobstawskiagent-ux/webskan-claude-plugin/plugin install webskan@webskan

Or from the shell:

claude plugin marketplace add kamilobstawskiagent-ux/webskan-claude-pluginclaude plugin install webskan@webskan

No account and no key are needed for the free plan. If you only want the MCP server without the skill:

claude mcp add --transport http webskan https://webskan.com/mcp

Use

/webskan:site-check https://mysite.com

or just ask: "audit https://mysite.com and fix the high-severity findings, then recheck".

Tools provided by the server: scan_website, audit_website, get_audit, recheck_website. Details, limits of the free plan and configuration for Cursor, VS Code, Codex CLI and other clients: https://webskan.com/developers/

Free plan limits

  • scan_website: 10 per hour per IP (120 per hour overall); results cached 24 h per host, kept 7 days.
  • audit_website / recheck_website: 2 per IP per 24 h and 1 per host per 24 h; 1-30 pages; results kept 30 days.
  • Public websites only - no localhost, private networks or sites behind a login.

Developer plan ($29/month): 30 whole-site audits per 24 h per key and no one-audit-per-host-per-day window. Pass the key as Authorization: Bearer <key> (an http server with headers in your MCP config). Details: https://webskan.com/developers/#teams

Layout

.claude-plugin/marketplace.json      marketplace "webskan"plugins/webskan/  .claude-plugin/plugin.json         plugin manifest  .mcp.json                          remote MCP server  skills/site-check/SKILL.md         the audit -> fix -> recheck loop

License

MIT. Contact: [email protected]

来源：README.md，提交 47dcb83

工具

4

scan_website

Quick website scan

Quick scan of one page (the URL you pass, usually the home page): Lighthouse mobile scores (performance, accessibility, best practices, SEO) with LCP/CLS/TBT/page weight/requests, plus HTTPS redirect, TLS, HSTS and security headers, title, meta description, H1, image alt texts, viewport, canonical, Open Graph, mixed content. Takes 30-60 s; waits up to 90 s and otherwise returns status "pending" with a scanId – call again with the same URL in 30 s. Results per host are cached for 24 h (field cached: true). Free, 10 calls per hour per IP. Use it right after a deploy as a smoke check; use audit_website for the whole site.

输入参数url必填

audit_website

Full website audit (async)

Starts a full technical audit of a whole website and returns immediately with an auditId (poll get_audit every 20-30 s; typically done in 1-5 min). The audit crawls up to `pages` pages (1-30, default 15) following internal links and the sitemap, and checks: broken internal/external links with the pages they sit on, per-page SEO (title, description, H1, canonical, alt texts, Open Graph), Lighthouse mobile and desktop, WCAG accessibility (axe) with selectors, HTTPS/TLS/security headers, robots/sitemap, platform detection and customer journeys (menu, search, forms, 404). No LLM, deterministic, read-only. Free plan: 2 audits per IP per 24 h and 1 per host per 24 h (a repeat call for the same host returns the existing audit). With Authorization: Bearer <Webskan Developer license key>: 30 per 24 h.

输入参数url必填pages

get_audit

Get audit status / result

Returns the status (queued / running with ETA) or the finished result of an audit started with audit_website or recheck_website: summary counts by severity, Lighthouse mobile+desktop scores, findings sorted high → medium → low → info (each with id, area, severity, title, detail and the pages it was found on), pagesCrawled, finalUrl, platform. For a re-check it also returns diff: fixed / open / new / unverified findings and Lighthouse before/after. Poll every 20-30 s while status is queued or running.

输入参数auditId必填

recheck_website

Re-check after fixes (diff)

Runs the same audit again (same URL, same number of pages) linked to the original auditId, so get_audit returns a diff: fixed / still open / new / unverified findings and Lighthouse before → after. Call it after you have deployed fixes. Asynchronous like audit_website (returns a new auditId to poll with get_audit) and counted against the same limits (free: 2 audits per IP per 24 h).

输入参数auditId必填

版本历史

1
  1. v0.1.0最新Nov 7, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分