Browser Use
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
电脑或云端✓ browser-use.com
Website Auditor
概览
作者提供的说明（英文原文）
AI visibility in ChatGPT, Gemini, Claude, Perplexity, Copilot & AI Overviews, plus site audits.
它能帮你做什么
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
- 连接方式: 在你的电脑上运行
- 传输方式: stdio
- 分类: 网页与浏览器
- 你需要填写：WA_API_KEY
安装
选择你使用的 AI 应用，然后复制设置。
通过 2/2 项检查 · 在你的电脑上运行
第一步：你用哪个 AI？
选择你用的应用，步骤会显示在下方。
可连接 Claude，但需要先准备
需要 Website Auditor 的密钥（在开发者网站注册，可能收费） · 需要先在电脑上安装 Node.js（只需一次） · 仅限电脑上的 Claude 应用（Windows 或 Mac），网页和手机不可用
打开电脑版 Claude 应用的设置文件
SettingsDeveloperEdit Config
粘贴这些设置并保存文件
{ "mcpServers": { "website-auditor": { "command": "npx", "args": [ "-y", "website-auditor-mcp" ], "env": { "WA_API_KEY": "your-value", "WA_API_BASE_URL": "your-value" } } } }只把密钥粘贴到应用的输入框里，不要粘贴到聊天中或发给任何人
退出 Claude 再重新打开
试一试
用 Website Auditor 告诉我你能帮我做什么，然后做一件给我看✓ 如果 Claude 说正在使用 Website Auditor，或回答中出现 Website Auditor 的工具名称，就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 Website Auditor
Website Auditor 需要安装在你的电脑上，而 ChatGPT 只能连接在网上运行的服务器
你可以改用这些方式
A · 使用能连接 Website Auditor 的应用
- 需要 Website Auditor 的密钥（在开发者网站注册，可能收费） · 需要先在电脑上安装 Node.js（只需一次） · 仅限电脑上的 Claude 应用（Windows 或 Mac），网页和手机不可用
- 需要 Website Auditor 的密钥（在开发者网站注册，可能收费） · 需要先在电脑上安装 Node.js（只需一次）
- 需要 Website Auditor 的密钥（在开发者网站注册，可能收费） · 需要先在电脑上安装 Node.js（只需一次）
- 需要 Website Auditor 的密钥（在开发者网站注册，可能收费） · 需要先在电脑上安装 Node.js（只需一次）
B · 网页与浏览器 类中能连接 ChatGPT 的其他服务器
从同类中使用较多的里挑选，仅限用地址即可连接、无需密钥的
- webclaw✓ ChatGPT
- Actionbook✓ ChatGPT
- Flowershow✓ ChatGPT
可连接 Claude Code，但需要先准备
需要 Website Auditor 的密钥（在开发者网站注册，可能收费） · 需要先在电脑上安装 Node.js（只需一次）
打开终端
Mac：按 Command+空格，输入 Terminal · Windows：打开 PowerShell
粘贴这条命令并按 Enter
claude mcp add website-auditor --env WA_API_KEY=your-value --env WA_API_BASE_URL=your-value -- npx -y website-auditor-mcp按 Enter 前，把“your-value”改成你的密钥
只把密钥粘贴到应用的输入框里，不要粘贴到聊天中或发给任何人
在 Claude Code 中输入 /mcp
应能看到 Website Auditor 在列表中并显示已连接
试一试
用 Website Auditor 告诉我你能帮我做什么，然后做一件给我看✓ 如果 Claude Code 说正在使用 Website Auditor，或回答中出现 Website Auditor 的工具名称，就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor，但需要先准备
需要 Website Auditor 的密钥（在开发者网站注册，可能收费） · 需要先在电脑上安装 Node.js（只需一次）
填写你的密钥
在 Website Auditor 的设置中，WA_API_KEY, WA_API_BASE_URL 还是空的，填入你的密钥并保存
只把密钥粘贴到应用的输入框里，不要粘贴到聊天中或发给任何人
在 Cursor 中以 Agent 模式打开 AI 聊天
试一试
用 Website Auditor 告诉我你能帮我做什么，然后做一件给我看✓ 如果 Cursor 说正在使用 Website Auditor，或回答中出现 Website Auditor 的工具名称，就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code，但需要先准备
需要 Website Auditor 的密钥（在开发者网站注册，可能收费） · 需要先在电脑上安装 Node.js（只需一次）
填写你的密钥
在 Website Auditor 的设置中，WA_API_KEY, WA_API_BASE_URL 还是空的，填入你的密钥并保存
只把密钥粘贴到应用的输入框里，不要粘贴到聊天中或发给任何人
在 VS Code 中以 Agent 模式打开 AI 聊天
试一试
用 Website Auditor 告诉我你能帮我做什么，然后做一件给我看✓ 如果 VS Code 说正在使用 Website Auditor，或回答中出现 Website Auditor 的工具名称，就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
开发者专用：终端命令和 JSON 设置
安装在电脑上
Claude Code
claude mcp add website-auditor --env WA_API_KEY=your-value --env WA_API_BASE_URL=your-value -- npx -y website-auditor-mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"website-auditor": {
"command": "npx",
"args": [
"-y",
"website-auditor-mcp"
],
"env": {
"WA_API_KEY": "your-value",
"WA_API_BASE_URL": "your-value"
}
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"website-auditor": {
"command": "npx",
"args": [
"-y",
"website-auditor-mcp"
],
"env": {
"WA_API_KEY": "your-value",
"WA_API_BASE_URL": "your-value"
}
}
}
}VS Code (mcp.json)
{
"servers": {
"website-auditor": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"website-auditor-mcp"
],
"env": {
"WA_API_KEY": "your-value",
"WA_API_BASE_URL": "your-value"
}
}
}
}需要你填写的值
WA_API_KEY机密 envOptional: get_sample_audit works with no key and returns a full report in the real output format. Every other tool requires a key, and minting one requires an active Website Auditor subscription ($49…WA_API_BASE_URLenvBase URL of the Website Auditor API this server wraps. Defaults to the public production host.
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。
一览
哪些应用可以使用它
依据这个服务器的连接方式和各应用自己的文档，检查于 2026年11月10日。
在你的电脑上运行，适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
它能做什么
它在你的电脑上运行；安装后，工具列表会显示在你的 AI 应用中。
基础检查i
我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月11日
- ✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 SpikeyCoder 验证，该账户拥有此仓库
- ✓ 通过
仍在维护
代码最后更新于今天
- … 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
- – 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
- – 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
- … 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行；我们只能读取互联网端点的工具列表
讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
用户评价
还没有评价
与“网页与浏览器”中的其他服务器比较i
- 星标数多于此分类中其他 1458 个服务器的 77%
- 发布到注册中心的时间比此分类中其他 1458 个服务器的 99% 更新
- 基础检查结果等于或优于此分类中其他 1458 个服务器的 100%
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。
常见问题
Website Auditor 安全吗？
它在 2 项适用的基础检查中通过了 2 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。
它需要哪些密钥或代码？
你需要填写：WA_API_KEY
它在我的电脑上运行还是在云端？
它在你的电脑上运行。你的 AI 应用会在需要时启动它，数据不会经过作者的服务器（除非它自己调用在线服务）。
它还在维护吗？
GitHub 仓库最后更新于今天，最新版本（1.0.30）于今天进入注册中心。
哪些应用可以使用它？
支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
有什么可以替代它？
同一分类中有：Browser Use, Scrapling MCP Server, Chrome DevTools MCP
替代选择
同一分类中其他作者的服务器，按星标数排序。
如何看卡片：↓ 每周下载量i★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Scrapling MCP Server
Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.
在你的电脑上运行
作者的 README
打开 README
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Website Auditor MCP
An MCP server for [website-auditor.io](https://website-auditor.io) — AI-visibility (GEO) and site-audit tools you can call from any MCP client (Claude Desktop, Claude Code, Cursor, Codex, and other agents).
Ask an agent *"does ChatGPT recommend my business?"*, *"what's my AI-visibility score?"*, *"audit example.com"*, or *"how do I stack up against my competitors?"* and it answers with real data — an overall AI-visibility score (0–100), a per-engine breakdown across ChatGPT, Perplexity, Claude, Gemini, Microsoft Copilot and Google AI Overviews, a full site audit (security, performance, crawlability and markup), competitor comparisons, and ongoing monitoring.
The server is a thin, authenticated wrapper over the Website Auditor API — the audit engine, AI-visibility scoring and monitoring live in that service; this server just makes them available to agents.
Tools
| Tool | Tier | What it does |
|---|---|---|
get_sample_audit | Free — no key | A complete sample report for example.com in the exact shape a real audit returns. Needs no API key, no subscription and no network. Try this first to see what you'd be buying. |
get_ai_visibility | Pro | Current AI-visibility score (0–100) + per-engine breakdown (ChatGPT, Perplexity, Claude, Gemini, Microsoft Copilot, Google AI Overviews) + the top competitor appearing in your place. Pro subscribers also get trend: 7- and 30-day score movement from stored snapshot history for the question this audit asked, ending at its snapshot and compared only between measured snapshots that asked it, the overall further only between endpoints the same engines answered (a window engines differed over carries its engine deltas and an overall_note saying which answered each; null, with a note, when the audit stored no measured snapshot). Also recommendation_gap (points behind the top beatable rival in the answers that *recommend* you, overall and per engine, with one sentence to read back; marketplaces, delivery apps, directories and national chains are not beatable rivals) and stance_counts (answers that recommended, mentioned or cautioned against you), each present only when measured. Also questions_asked: the questions put to the assistants for the score, when the report recorded them. |
run_audit | Pro, rate-limited | Full one-time audit → category scores (AI visibility, crawlability and markup as seo, security, performance) + top issues + a shareable report URL. Also recommendation_gap and stance_counts (see get_ai_visibility), each present only when measured. |
get_changes | Pro | What changed in the AI-visibility score — the change in the overall score and the per-engine score changes, for engines measured both times, the overall only when the same engines answered both snapshots (else it is null with an overall_note naming which answered each, and the per-engine changes stand alone); summary says the change in plain sentences; competitor_changes, new_issues and resolved_issues are always empty. Only between two snapshots that asked the same question (the same business name, market and queries), read from the domain's series: its measured weekly re-audits and any audit that asked the same question as the newest recorded one, while it has no gap longer than four weeks and a day from the newest weekly re-audit that recorded its question, through each later snapshot of the series (weekly re-audits included, recorded or not), to the newest measured snapshot. When there is no such pair it says why instead of a number, with the date the series re-baselined when it did. The domain need not be tracked: history accrues from any audit of it, tracked or not — track_site adds the weekly re-audits to the series, it is not a precondition. |
compare_competitors | Pro | Head-to-head AI-visibility ranking against named competitor domains + where each appears that you don't. Quota-aware: caps the audit fan-out to your remaining daily quota, reuses recent cached audits, and reports any competitors it had to skip rather than dropping them silently. Also recommendation_gap: how far behind the competitor you trail most you are (ties on identical counts are all named), each side as a share of its own answers, over the assistants that answered for BOTH sites; same_questions says whether both audits asked the same set of questions (null when either did not record them) and assistants which assistants the figures are over. Present only when both audits recorded stances. |
track_site | Pro | Start (or stop) weekly monitoring of a site's AI visibility. Its weekly re-audits join the history get_changes reads from, which audits accrue tracked or not — monitoring watches a site, it does not enable get_changes. |
untrack_site | Pro | Stop monitoring a site and free up a monitoring slot. Deletes the site's monitoring enrollment; past audits are kept. |
list_tracked_sites | Pro | List the sites you're monitoring, with cadence, active state, and slots used/remaining. |
get_monitoring_status | Pro | A glanceable dashboard across all tracked sites — latest score of each site's series (the series get_changes reads), the date of each one's last scheduled run and when the next runs, and the most recent like-for-like change (or a note, or the summary, saying why there is none), shown as its per-engine changes with a note naming the engines when different ones answered the two snapshots; like get_changes, its change carries competitor_changes, new_issues and resolved_issues, always empty. |
list_fixes | Pro | A tracked site's ready-made fixes ("Get this fix"), top first: whether each is needed and why, whether the site's platform can take it, and its newest request and status (live / missing). Records nothing. |
get_fix_facts | Pro | The business facts the fixes are written from, to show the owner: what the site says, what they confirmed, the business name the audits found, and seen (exactly what was shown, sent back unchanged to confirm). |
get_fix | Pro | "Get this fix": the fix served finished (structured data plus About/FAQ text, an llms.txt, or robots.txt lines that let blocked AI assistants in), the first two written only from the owner's confirmed facts, each block ready to copy, with paste steps for the site's platform and copy_all where an agent edits the site. Each call is recorded as a request. Before the facts are confirmed it answers status: "confirm_first" with the facts to show the owner; when the newest audit found nothing to change, status: "nothing_to_fix". |
confirm_facts | Pro | Confirms the facts the owner confirmed or corrected, sending back exactly the seen they were shown — never on the owner's behalf. status: "facts_changed" when the site changed since. |
check_fix | Pro | "I've added it": reads the live site for a fix request and says it's live or names what's missing. Once a minute per request (CHECKED_RECENTLY with retry_after). |
check_upgrade_status | Any valid key | Your own subscription standing — tier, status, period end, and what upgrading unlocks (starting Pro requires a payment method and accepting the Terms). Consumes no audit quota. |
Prompts
Clients that support MCP prompts (Claude Desktop, claude.ai) render these as something you can pick from a menu, so you don't have to phrase the request yourself or know which tool to ask for. In clients that don't surface prompts (Codex, currently), nothing is lost but the menu — ask in words and the same tools run.
| Prompt | Needs a key? | What it does |
|---|---|---|
| See a sample report | No | Walks through a complete report for example.com. No arguments, no setup — one click from any install. |
| Check my AI visibility | Pro | Runs get_ai_visibility for a domain you name, then explains the score, which assistants name the business, and who is named instead. |
| Run a full site audit | Pro | Runs run_audit for a domain and summarises it by category, with the three fixes that matter most. |
| Compare me to a competitor | Pro | Runs compare_competitors for your domain against a named rival, and explains where they get named and you don't. |
Each Pro prompt falls back to get_sample_audit when no API key is configured, so you always get output rather than an error.
Naming the business (optional)
get_ai_visibility and run_audit both accept two optional arguments that decide *what question* the AI-visibility check actually asks. compare_competitors accepts business_location only — see below for why it takes no name:
| Argument | Omitted | Supplied |
|---|---|---|
business_name | Detected from the site, and flagged with name_warning when it could not be verified | Taken as fact and recorded as caller-supplied — which suppresses the warning |
business_location | Detected from the site; if nothing is found the questions widen to the country, or drop the place entirely | Scopes the questions to that place |
Supply a name only when you actually know it. A supplied name overrides detection and is treated as confirmed, so a guess is scored exactly as if a human had verified it — and silences the warning that would have told you otherwise. Leaving it out is the safer default: detection is transparent about its own uncertainty.
The same applies to location, in the other direction. Omitting it is correct for a national or global business and wrong for a local one, since a local business measured without a place is measured against the wrong queries.
On `compare_competitors`: it takes business_location and applies it to your site *and every competitor*, because a comparison asks about one market — scoring you locally while scoring your rivals globally would rank the answers to two different questions. It deliberately takes no business_name: a name identifies one business, and forwarding yours to your competitors would score every one of them as you. The result names the market it used, so a scoped comparison is never mistaken for a global one.
"Check AI visibility for hawaiibackroad.com,the business is Big Island Backroad Adventures in Hilo, HI"
Install & configure
The server runs directly via npx — no clone or build required.
Try it before you buy it. Install with no API key at all and ask your agent for a *sample audit* — get_sample_audit returns a full report for example.com in the exact format a real run produces, so you can check the shape fits your needs first.
Pricing. Auditing real domains needs a Website Auditor subscription at $49/month — eligible new customers get a 7-day free trial (payment method required to start; no charge until the trial ends; customers who used a trial in the last 12 months are billed immediately). Sign up and create an API key at [api.website-auditor.io/admin_portal](https://api.website-auditor.io/admin_portal/?source=mcp), then set it as WA_API_KEY below. There is no free API tier — a key only functions with an active subscription.
Claude Desktop (claude_desktop_config.json), Cursor (~/.cursor/mcp.json), and most other clients use the same mcpServers shape:
{"mcpServers": { "website-auditor": { "command": "npx", "args": ["-y", "website-auditor-mcp"], "env": { "WA_API_KEY": "wa_your_key_here" } } } }
Claude Code — add it from the CLI:
claude mcp add website-auditor -e WA_API_KEY=wa_your_key_here -- npx -y website-auditor-mcpCodex — the CLI, IDE extension and ChatGPT desktop app all read the same ~/.codex/config.toml, so one of these covers all three:
codex mcp add website-auditor --env WA_API_KEY=wa_your_key_here -- npx -y website-auditor-mcp[mcp_servers.website-auditor]command