pageaudit

Technical SEO audit with the ready-made fix for each finding. Pay per call via x402 or credit.

使うべきか

品質と安全性

B
説明の品質
94%
スキーマの完全性
75%
命名の品質
90%
ポイズニングのリスク
80%
権限の一致
100%
プロトコルへの準拠
100%

検出事項(4)

  • HIGHTool poisoning patterns detected
  • MEDIUMTool 'get_patch' description contains placeholder textget_patch 内
  • LOWTool 'get_badge' description lacks action verbget_badge 内
  • INFOTool description contains placeholder or incomplete textget_patch 内

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~3,085トークン数(ツール定義)
~594 B一般的なレスポンスサイズ
注意への影響は大きい(128k コンテキストの 2.41%)

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

{
  "mcpServers": {
    "pageaudit": {
      "url": "https://pageaudit.online/mcp"
    }
  }
}

リモートエンドポイント

https://pageaudit.online/mcpstreamable-http

できること

ツール一覧

ツール(20)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢api_index

Discovers the whole PageAudit API (self-describing index).

入力スキーマ

{
  "type": "object",
  "properties": {}
}
🟢health

Liveness and the commit deployed right now — it is how the smoke waits for its own deploy.

入力スキーマ

{
  "type": "object",
  "properties": {}
}
🟢list_tools

Lists the micro-tools (title, meta, canonical, OG, JSON-LD…).

入力スキーマ

{
  "type": "object",
  "properties": {}
}
🟢get_tool(slug)

Copy and checks of one micro-tool by slug (e.g. title-tag-checker).

入力スキーマ

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "tool slug"
    }
  },
  "required": [
    "slug"
  ]
}
🟢audit_url(url, guest_token)

Audits a URL: SEO (meta and X-Robots-Tag, HTML and Link canonical), JSON-LD parsing, robots.txt decided per crawler for this path (Googlebot, Bingbot, AI search and training crawlers), real-user Core Web Vitals from the Chrome UX Report, llms.txt, security.txt, API catalog, function-matched well-known files, favicon response and missing-page probe. A firewall or rate limit answering instead of the page comes back as 502 `target_blocked`, never as a score. Returns evidence, limits and fixes without a tab; not a security/accessibility certification. This is the product for agents. Past the IP's daily allowance the response is **402 with `accepts[]`** and `code: allowance_spent` — pay and repeat the same call. There is no captcha: people and agents pay the same way. The free alternative: a person signs in with an account to get the trial.

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "absolute URL to audit"
    },
    "guest_token": {
      "type": "string",
      "description": "optional pa_…"
    }
  },
  "required": [
    "url"
  ]
}
🟡create_guest

Creates a guest token pa_… for the tab workspace. Keep the token: it is the identity of the tabs and of the audits tied to them.

入力スキーマ

{
  "type": "object",
  "properties": {}
}
🟢list_tabs(guest_token)

Lists the owner's tabs (guest or session). One call draws the whole screen: tabs, the focused tab, its last report, remaining allowance and prices.

入力スキーマ

{
  "type": "object",
  "properties": {
    "guest_token": {
      "type": "string"
    }
  },
  "required": [
    "guest_token"
  ]
}
🟡create_tab(guest_token, url, alias)

Opens a tab for a URL in the workspace. Past the free tab allowance it answers 402 with `accepts[]`: pay and repeat.

入力スキーマ

{
  "type": "object",
  "properties": {
    "guest_token": {
      "type": "string"
    },
    "url": {
      "type": "string",
      "description": "The URL the tab will follow."
    },
    "alias": {
      "type": "string",
      "description": "Label to recognise the tab in the list."
    }
  },
  "required": [
    "guest_token",
    "url"
  ]
}
⚪run_tab(guest_token, id)

Re-audits the tab's URL. Consumes the same daily allowance as `POST /api/audit` — past it, 402 with `accepts[]`.

入力スキーマ

{
  "type": "object",
  "properties": {
    "guest_token": {
      "type": "string"
    },
    "id": {
      "type": "string",
      "description": "ID of the tab to re-audit."
    }
  },
  "required": [
    "guest_token",
    "id"
  ]
}
🟢tab_history(guest_token, id, limit)

The tab's previous runs and what changed between each one and the one before it (score delta, findings that appeared and that disappeared). Every run has always been kept; this is where you read the series. Each entry carries the score, the counts and a `change` with the point delta and the findings that appeared (`broke`) or disappeared (`fixed`) since the previous run — compared by finding code, never by message. Runs older than the watch feature are matched by URL.

入力スキーマ

{
  "type": "object",
  "properties": {
    "guest_token": {
      "type": "string"
    },
    "id": {
      "type": "string",
      "description": "ID of the tab whose runs you want."
    },
    "limit": {
      "type": "number",
      "description": "how many runs, newest first (default 20, max 100)"
    }
  },
  "required": [
    "guest_token",
    "id"
  ]
}
🔴watch_tab(guest_token, id, monitor, monitor_email)

Turns the daily watch on or off for a tab: it re-audits the page once a day and e-mails when the score drops or a new error/warning appears. Needs the signed-in account (its browser session cookie); a guest token gets 403 `account_required`. With `monitor: true` the page is re-audited once a day and an e-mail goes out when the score drops or a new error/warning appears — never on an improvement. Watching needs an account (the alert has to reach someone) and each account watches a limited number of pages.

入力スキーマ

{
  "type": "object",
  "properties": {
    "guest_token": {
      "type": "string",
      "description": "guest pa_… — refused: a guest has no e-mail to warn"
    },
    "id": {
      "type": "string",
      "description": "ID of the tab to change."
    },
    "monitor": {
      "type": "boolean",
      "description": "true watches, false stops watching"
    },
    "monitor_email": {
      "type": "string",
      "description": "where the alert goes; empty = account e-mail"
    }
  },
  "required": [
    "guest_token",
    "id",
    "monitor"
  ]
}
🟡lab_test(guest_token, id, strategy)

Starts a lab test of an audit's page: Lighthouse run by Google PageSpeed Insights (performance, accessibility, best practices, SEO). Answers 202 at once; the test takes ~25 s to 2+ minutes — then read it with lab_result. Does not change the audit score. Answers **202** at once; the test runs for ~25 s to over 2 minutes and its summary is stored in the audit (`summary.lab.<strategy>`), so it comes back in `GET /api/audits/:id`, in the tab and in the shared report. It does not change the audit score. Calling again while the same strategy is running does not start a second test. Limits: 4 tests at a time on the server, 6 per network per hour and 500 per day for the whole product. Free: no x402 charge.

入力スキーマ

{
  "type": "object",
  "properties": {
    "guest_token": {
      "type": "string"
    },
    "id": {
      "type": "string",
      "description": "audit id"
    },
    "strategy": {
      "type": "string",
      "description": "mobile (default) or desktop"
    }
  },
  "required": [
    "guest_token",
    "id"
  ]
}
🟢lab_result(guest_token, id, wait)

The lab tests of an audit (mobile and desktop): running, finished with scores, metrics and biggest savings, or failed. With wait (up to 25) it answers as soon as a running test finishes. Long-poll: with `wait` the answer comes as soon as a running test finishes, or after `wait` seconds with `status: running`. Repeat until it is not running.

入力スキーマ

{
  "type": "object",
  "properties": {
    "guest_token": {
      "type": "string"
    },
    "id": {
      "type": "string",
      "description": "audit id"
    },
    "wait": {
      "type": "number",
      "description": "seconds to wait for a running test, 0–25"
    }
  },
  "required": [
    "guest_token",
    "id"
  ]
}
🟢get_audit(guest_token, id)

Re-reads an audit already made, with `fixes` (the ready fix for each finding). Re-reading costs nothing and does not count against the allowance — the page's HTML is not kept, but the report is.

入力スキーマ

{
  "type": "object",
  "properties": {
    "guest_token": {
      "type": "string"
    },
    "id": {
      "type": "string",
      "description": "Audit ID, from `Audit.id`."
    }
  },
  "required": [
    "guest_token",
    "id"
  ]
}
🟢get_patch(guest_token, id)

The consolidated patch of an audit: <head> block to paste, files to create and templates with placeholders. No model — only facts from the page. Each finding becomes a fix in one of three classes: `deterministico` (comes whole from what the page declares: final URL, title, description, OG), `molde` (a tag with a marked placeholder, like `{{TITULO}}`, and the suggested source) or `sem_patch` (a decision or infrastructure, with the instruction). Nothing is invented by a model.

入力スキーマ

{
  "type": "object",
  "properties": {
    "guest_token": {
      "type": "string"
    },
    "id": {
      "type": "string",
      "description": "Audit ID, from `Audit.id`."
    }
  },
  "required": [
    "guest_token",
    "id"
  ]
}
🟢get_badge(slug)

Metadata and markdown of the SVG badge of a shared report.

入力スキーマ

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "24-char public slug"
    }
  },
  "required": [
    "slug"
  ]
}
🟢embed_snippet(brand, color, theme, url)

The embeddable widget's snippet, already assembled with the site's name and colour — one script tag, no account, no lead capture. One script tag puts the audit form on your own site, with your name and colour, and no account or key. Send the same query you would send to `/embed` and the answer comes back with `snippet` already assembled. The widget never asks the visitor for an e-mail.

入力スキーマ

{
  "type": "object",
  "properties": {
    "brand": {
      "type": "string",
      "description": "site name shown above the form"
    },
    "color": {
      "type": "string",
      "description": "accent colour in hex"
    },
    "theme": {
      "type": "string",
      "description": "auto, light or dark"
    },
    "url": {
      "type": "string",
      "description": "optional URL to pre-fill"
    }
  }
}
🟢billing

Free plan, prices, x402 parameters and the trial offer: an account gets 90 days without paywall from its first use (`trial` field; with a session it shows the state).

入力スキーマ

{
  "type": "object",
  "properties": {}
}
🟡contact(name, email, message, tipo, empresa, ...)

Write to the people behind the product: a question, or a sponsorship/partnership/advertising proposal. Free, no captcha and no payment; one message every 10 s per network (one that arrives sooner waits its turn). One route for a question and for a sponsorship, partnership or ad proposal (`tipo`, with the placements of `GET /api/partners`). No captcha, no account, no payment. One message every 10 seconds per network: one that arrives sooner waits its turn and then goes out — no error. The message reaches the team by e-mail, with `email` as the reply address.

入力スキーマ

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "What to call the person writing."
    },
    "email": {
      "type": "string",
      "description": "Where to reply."
    },
    "message": {
      "type": "string",
      "description": "What you want to say."
    },
    "tipo": {
      "type": "string",
      "enum": [
        "patrocinio",
        "parceria",
        "anuncio"
      ],
      "description": "Proposal: `patrocinio`, `parceria` or `anuncio`. Turns on the fields below."
    },
    "empresa": {
      "type": "string",
      "description": "Who is proposing, when it is a company."
    },
    "site": {
      "type": "string",
      "description": "Website of who is proposing."
    },
    "orcamento": {
      "type": "string",
      "enum": [
        "ate_100",
        "100_500",
        "500_2000",
        "2000_mais",
        "a_combinar"
      ],
      "description": "`ate_100`, `100_500`, `500_2000`, `2000_mais` or `a_combinar`."
    },
    "espaco": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Placement ids from `GET /api/partners`, up to 6."
    },
    "duracao": {
      "type": "string",
      "enum": [
        "30",
        "90",
        "365"
      ],
      "description": "Exposure in days: `30`, `90` or `365`."
    },
    "pagamento": {
      "type": "string",
      "enum": [
        "usdc",
        "deposito",
        "a_combinar"
      ],
      "description": "`usdc`, `deposito` or `a_combinar`."
    }
  },
  "required": [
    "name",
    "email",
    "message"
  ]
}
🟢pricing

Current public prices and free allowances; no charge.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

推奨プロンプト

retrieve_data
Get details about [item] from pageaudit
想定されるツール: get_tool
fetch_info
Fetch [information type] using pageaudit
想定されるツール: get_tool
list_items
List all [items] available in pageaudit
想定されるツール: list_tools
browse_collection
Show me the [collection] from pageaudit
想定されるツール: list_tools
explore_workflow
List available [items], then get details for each one using pageaudit
想定されるツール: list_toolsget_tool

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 20 件
検証済みバージョンは記録されていませんツール 18 件