citation-tracker

Checks whether AI search engines cite your domain for a prompt. From $0.15/call via x402 or Stripe.

使うべきか

品質と安全性

A
説明の品質
98%
スキーマの完全性
100%
命名の品質
70%
ポイズニングのリスク
100%
権限の一致
100%
プロトコルへの準拠
100%

検出事項(4)

  • LOWTool 'citation_tracker_check_perplexity' name length outside 3-30 rangecitation_tracker_check_perplexity 内
  • LOWTool 'citation_tracker_shortlist_gate' name length outside 3-30 rangecitation_tracker_shortlist_gate 内
  • LOWTool 'citation_tracker_monitor_status' name length outside 3-30 rangecitation_tracker_monitor_status 内
  • LOWTool 'citation_tracker_monitor_cancel' name length outside 3-30 rangecitation_tracker_monitor_cancel 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

~2,223トークン数(ツール定義)
~1.9 KB一般的なレスポンスサイズ
注意への影響は中程度(128k コンテキストの 1.74%)

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": {
    "citation-tracker": {
      "url": "https://citation-tracker.pixelcove.co/mcp"
    }
  }
}

リモートエンドポイント

https://citation-tracker.pixelcove.co/mcpstreamable-http

できること

ツール一覧

ツール(8)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢citation_tracker_check(prompt, engines, targets)

Sends one prompt to 1 to 4 search assistants (Perplexity, OpenAI, Anthropic, Gemini) and reports whether each cites your target domains: cited status, citation count, cited domains, model, and a structured error per engine. Started concurrently; a failed engine returns `cited: null` and does not block the others (PD7). Paid, $0.75/call; read-only and safe to retry.

入力スキーマ

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "minLength": 1,
      "maxLength": 4000,
      "description": "The prompt to send to the search assistant(s), verbatim. 1 to 4000 characters."
    },
    "engines": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "perplexity",
          "openai",
          "anthropic",
          "gemini"
        ]
      },
      "minItems": 1,
      "maxItems": 4,
      "uniqueItems": true,
      "description": "1 to 4 distinct engines to check, from perplexity, openai, anthropic, gemini."
    },
    "targets": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 253,
        "pattern": "^(?:[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\\.)+[a-z]{2,63}$",
        "description": "A normalized domain, e.g. example.com (no scheme, no path, no whitespace, lowercase)."
      },
      "minItems": 1,
      "maxItems": 10,
      "description": "1 to 10 target domains to check for a citation."
    }
  },
  "required": [
    "prompt",
    "engines",
    "targets"
  ],
  "additionalProperties": false
}
🟢citation_tracker_check_one(prompt, engines, targets)

Sends one prompt to one search assistant (Perplexity, OpenAI or Gemini) and reports whether it cites your target domains: cited status, citation count, cited domains, model, and a structured error. For Claude, or several engines in one call, use citation_tracker_check. Paid, $0.15/call; read-only and safe to retry.

入力スキーマ

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "minLength": 1,
      "maxLength": 4000,
      "description": "The prompt to send to the search assistant(s), verbatim. 1 to 4000 characters."
    },
    "engines": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "perplexity",
          "openai",
          "gemini"
        ]
      },
      "minItems": 1,
      "maxItems": 1,
      "description": "Exactly one engine: perplexity, openai, or gemini."
    },
    "targets": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 253,
        "pattern": "^(?:[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\\.)+[a-z]{2,63}$",
        "description": "A normalized domain, e.g. example.com (no scheme, no path, no whitespace, lowercase)."
      },
      "minItems": 1,
      "maxItems": 10,
      "description": "1 to 10 target domains to check for a citation."
    }
  },
  "required": [
    "prompt",
    "engines",
    "targets"
  ],
  "additionalProperties": false
}
🟢citation_tracker_check_perplexity(prompt, targets)

Sends one prompt to Perplexity (sonar) and reports whether it cites your target domains, with citation count and cited domains. Free: one call per caller and 100 calls total per UTC day; both limits fail closed. A real live evaluation before you pay for citation_tracker_check.

入力スキーマ

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "minLength": 1,
      "maxLength": 4000,
      "description": "The prompt to send to the search assistant(s), verbatim. 1 to 4000 characters."
    },
    "targets": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 253,
        "pattern": "^(?:[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\\.)+[a-z]{2,63}$",
        "description": "A normalized domain, e.g. example.com (no scheme, no path, no whitespace, lowercase)."
      },
      "minItems": 1,
      "maxItems": 10,
      "description": "1 to 10 target domains to check for a citation."
    }
  },
  "required": [
    "prompt",
    "targets"
  ],
  "additionalProperties": false
}
🟢citation_tracker_shortlist_gate(prompt, brand_terms, product_terms)

Checks whether ChatGPT would search the web for one prompt and whether its first search query names any of your supplied brand or product terms (whole-word match). Use it to gate a prompt before spending on citation_tracker_check. Paid, $0.20/call; read-only and safe to retry.

入力スキーマ

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "minLength": 1,
      "maxLength": 4000,
      "description": "The prompt to send to the search assistant(s), verbatim. 1 to 4000 characters."
    },
    "brand_terms": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 100
      },
      "minItems": 1,
      "maxItems": 20,
      "description": "1 to 20 brand terms to look for in the first search query."
    },
    "product_terms": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 100
      },
      "minItems": 0,
      "maxItems": 50,
      "default": [],
      "description": "0 to 50 product terms to look for in the first search query."
    }
  },
  "required": [
    "prompt",
    "brand_terms"
  ],
  "additionalProperties": false
}
🔴citation_tracker_monitor_7(prompt, targets, engines, cadence)

Buys a monitor: 7 recurring runs of citation_tracker_check for one prompt and 1 to 10 target domains, daily or weekly. The first run happens now and is returned. Later runs are read with citation_tracker_monitor_status using the returned monitor_id (the only credential; it is not recoverable). Each run flags which target domains changed since the last run. Paid once, $4.2 for the term ($0.6/check); no refund of unused runs; cancel any time with citation_tracker_monitor_cancel. Retains the prompt, domains and results until 30 days after the last run or until cancelled.

入力スキーマ

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "minLength": 1,
      "maxLength": 4000,
      "description": "The prompt to send to the search assistant(s), verbatim. 1 to 4000 characters."
    },
    "targets": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 253,
        "pattern": "^(?:[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\\.)+[a-z]{2,63}$",
        "description": "A normalized domain, e.g. example.com (no scheme, no path, no whitespace, lowercase)."
      },
      "minItems": 1,
      "maxItems": 10,
      "description": "1 to 10 target domains to check for a citation."
    },
    "engines": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "perplexity",
          "openai",
          "anthropic",
          "gemini"
        ]
      },
      "minItems": 1,
      "maxItems": 4,
      "uniqueItems": true,
      "description": "1 to 4 search assistants to run on every check."
    },
    "cadence": {
      "type": "string",
      "enum": [
        "daily",
        "weekly"
      ],
      "description": "How often to re-run the check."
    }
  },
  "required": [
    "prompt",
    "targets",
    "engines",
    "cadence"
  ],
  "additionalProperties": false
}
🔴citation_tracker_monitor_30(prompt, targets, engines, cadence)

Buys a monitor: 30 recurring runs of citation_tracker_check for one prompt and 1 to 10 target domains, daily or weekly. The first run happens now and is returned. Later runs are read with citation_tracker_monitor_status using the returned monitor_id (the only credential; it is not recoverable). Each run flags which target domains changed since the last run. Paid once, $18 for the term ($0.6/check); no refund of unused runs; cancel any time with citation_tracker_monitor_cancel. Retains the prompt, domains and results until 30 days after the last run or until cancelled.

入力スキーマ

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "minLength": 1,
      "maxLength": 4000,
      "description": "The prompt to send to the search assistant(s), verbatim. 1 to 4000 characters."
    },
    "targets": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 253,
        "pattern": "^(?:[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\\.)+[a-z]{2,63}$",
        "description": "A normalized domain, e.g. example.com (no scheme, no path, no whitespace, lowercase)."
      },
      "minItems": 1,
      "maxItems": 10,
      "description": "1 to 10 target domains to check for a citation."
    },
    "engines": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "perplexity",
          "openai",
          "anthropic",
          "gemini"
        ]
      },
      "minItems": 1,
      "maxItems": 4,
      "uniqueItems": true,
      "description": "1 to 4 search assistants to run on every check."
    },
    "cadence": {
      "type": "string",
      "enum": [
        "daily",
        "weekly"
      ],
      "description": "How often to re-run the check."
    }
  },
  "required": [
    "prompt",
    "targets",
    "engines",
    "cadence"
  ],
  "additionalProperties": false
}
🟢citation_tracker_monitor_status(monitor_id)

Reads a monitor: remaining runs, next run time, and every run so far (most recent first) with the same per-engine rows as citation_tracker_check plus changed_since_last per target domain. Free. Needs the monitor_id.

入力スキーマ

{
  "type": "object",
  "properties": {
    "monitor_id": {
      "type": "string",
      "minLength": 8,
      "maxLength": 64,
      "pattern": "^ctm_[A-Za-z0-9_-]+$",
      "description": "The monitor id returned by citation_tracker_monitor_7 or _30. It is the only credential; keep it."
    }
  },
  "required": [
    "monitor_id"
  ],
  "additionalProperties": false
}
🔴citation_tracker_monitor_cancel(monitor_id)

Stops a monitor and deletes its prompt, domains and results. Unused runs are not refunded. Free. Needs the monitor_id.

入力スキーマ

{
  "type": "object",
  "properties": {
    "monitor_id": {
      "type": "string",
      "minLength": 8,
      "maxLength": 64,
      "pattern": "^ctm_[A-Za-z0-9_-]+$",
      "description": "The monitor id returned by citation_tracker_monitor_7 or _30. It is the only credential; keep it."
    }
  },
  "required": [
    "monitor_id"
  ],
  "additionalProperties": false
}

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 8 件
検証済みバージョンは記録されていませんツール 8 件
検証済みバージョンは記録されていませんツール 7 件