Ninar AI

Audit your brand's visibility across ChatGPT, Gemini, Claude, Perplexity + 6 more engines.

我該用這個嗎

品質與安全性

A
說明品質
100%
結構描述完整度
72%
命名品質
96%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

根據工具定義與協定合規性的自動化分析。

上下文成本

~892Token(工具定義)
~928 B典型回應大小
中等的注意力影響(128k 上下文的 0.70%)

這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。

安裝

一鍵安裝

將以下內容加入你的 `claude_desktop_config.json` 檔案:

{
  "mcpServers": {
    "ninar": {
      "url": "https://ninar.ai/mcp"
    }
  }
}

遠端端點

https://ninar.ai/mcpstreamable-http

它能做什麼

工具清單

工具(5)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢get_latest_score

Get the AI Visibility Index (0-100) for the signed-in user's most recently scanned brand, broken down by engine. Requires a free Ninar account (no credit card).

輸入結構描述

{
  "type": "object",
  "properties": {}
}
🟢scan_visibility(brand_name, category, city, country, use_case, ...)

Run an AI visibility scan for a brand. Pass `city` for a local-business check (ChatGPT + Gemini, city-scoped). Omit `city` for a multi-engine GEO scan across ChatGPT, Gemini, Perplexity, Claude, AI Overviews — engine count scales with the user's Ninar plan (free = 2).

輸入結構描述

{
  "type": "object",
  "properties": {
    "brand_name": {
      "description": "Brand to scan, e.g. 'Ninar', 'Joe's Pizza'.",
      "type": "string"
    },
    "category": {
      "description": "Category, e.g. 'AI visibility platform', 'pizza restaurant'.",
      "type": "string"
    },
    "city": {
      "description": "City for a local-business check. Omit for multi-engine GEO scan.",
      "type": "string"
    },
    "country": {
      "description": "Optional ISO country: us, gb, in, eu.",
      "type": "string"
    },
    "use_case": {
      "description": "Optional GEO use case, e.g. 'for sales teams'.",
      "type": "string"
    },
    "website": {
      "description": "Optional brand URL for GEO citation matching.",
      "type": "string"
    }
  },
  "required": [
    "brand_name",
    "category"
  ]
}
🟢list_content_gaps

List AI-generated content suggestions (FAQs, differentiators, use cases, about copy) the signed-in user can publish to close visibility gaps found in their latest scan.

輸入結構描述

{
  "type": "object",
  "properties": {}
}
🟢generate_content(gap_type)

Generate AI-optimized content (FAQ, about copy, use cases, differentiators) for the gaps in your latest scan. Returns full content text inline — no need to visit the dashboard. Pro plan or higher required. Pass gap_type='all' to get every block in one call.

輸入結構描述

{
  "type": "object",
  "properties": {
    "gap_type": {
      "description": "Which content block to generate. Use 'all' for everything in one call.",
      "enum": [
        "faq",
        "about",
        "use_cases",
        "differentiators",
        "all"
      ],
      "type": "string"
    }
  },
  "required": [
    "gap_type"
  ]
}
🟢audit_brand_visibility(entity, raw_evidence, taxonomy_id)

Check whether a brand or entity surfaced by an AI engine is a genuine competitor in your category (e.g. is 'Banner Life' actually a mortgage insurance competitor to Enact?). Uses dual-model verification with automatic escalation on disagreement. Returns a confirmed/rejected decision, confidence score, reasoning, and audit trail. Pro plan or higher required.

輸入結構描述

{
  "type": "object",
  "properties": {
    "entity": {
      "description": "Entity name to adjudicate, e.g. 'Banner Life', 'Enact Solar'.",
      "type": "string"
    },
    "raw_evidence": {
      "description": "Source text the entity appeared in. Should contain 'raw_answer_excerpt' and optionally 'entity_sentence' and 'source_probe_id'.",
      "properties": {
        "entity_sentence": {
          "type": "string"
        },
        "raw_answer_excerpt": {
          "type": "string"
        },
        "source_probe_id": {
          "type": "string"
        }
      },
      "required": [
        "raw_answer_excerpt"
      ],
      "type": "object"
    },
    "taxonomy_id": {
      "description": "Taxonomy registry to validate against. Default: pmi.v1",
      "type": "string"
    }
  },
  "required": [
    "entity",
    "raw_evidence"
  ]
}

建議的提示詞

retrieve_data
Get details about [item] from Ninar AI
預期的工具: get_latest_score
fetch_info
Fetch [information type] using Ninar AI
預期的工具: get_latest_score
list_items
List all [items] available in Ninar AI
預期的工具: list_content_gaps
browse_collection
Show me the [collection] from Ninar AI
預期的工具: list_content_gaps
explore_workflow
List available [items], then get details for each one using Ninar AI
預期的工具: list_content_gapsget_latest_score

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本5 個工具
已驗證未記錄版本5 個工具