Ai Visibility

io.github.sharozdawa由 GitHub 帳號 sharozdawa 發布v1.0.0更新於 Oct 24, 2026

Track brand visibility across ChatGPT, Perplexity, Claude, and Gemini.

已驗證STDIO僅桌面資料與分析商業與電商

概覽

AI 產生的概覽

一個本機 MCP 伺服器，回報 ChatGPT、Perplexity、Claude 與 Gemini 等 AI 平台如何提及某品牌，並提供評分、情感傾向與競品資料。

可以做什麼
檢查品牌在四個 AI 平台上的能見度，包含提及率、排名位置、情感傾向與競品分析；也可針對單一平台上的特定查詢，取得提及狀態、位置、上下文片段與情感傾向。計算 0-100 的整體能見度評分，附等級評定、各平台明細與改善建議。將 2 至 10 個品牌並排比較，提供排名結果與各平台分數。列出支援的平台及各自取得品牌資訊的方式。
適用情境
適合行銷人員或品牌方快速、可重複地了解 AI 助理如何描述自家品牌與競品，並取得改善 AI 能見度的優先建議。
執行需求
透過 stdio 在本機執行，通常以 npx 從 npm 套件 ai-visibility-mcp 啟動，因此需要 Node.js。未宣告需要帳號、API 金鑰或環境變數。可選的自架網頁儀表板需要資料庫連線字串。
安裝前請注意
README 說明結果使用帶種子的隨機數，因此評分是可重現的模擬結果，而非對 AI 平台的即時查詢，應視為參考而非實測。可選的儀表板設定要求在本地環境檔案中填寫資料庫連線字串。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Ai Visibility，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only，透過 STDIO。 STDIO 服務會啟動本機處理程序，因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

[圖片]

[npm version] [GitHub stars] [License] [PRs Welcome] [AI Visibility MCP server]

Know exactly how AI platforms talk about your brand.
Track mentions, sentiment, position, and competitors across the AI platforms that shape buying decisions.

Features

  • Multi-Platform Tracking — Monitor visibility across ChatGPT, Perplexity, Claude, and Gemini simultaneously
  • Visibility Scoring — Get a 0-100 score with tier ratings (Excellent / Good / Moderate / Low / Very Low)
  • Sentiment Analysis — Understand whether AI platforms describe your brand positively, neutrally, or negatively
  • Competitor Intelligence — See which competitors appear alongside your brand in AI responses
  • Brand Comparison — Compare up to 10 brands side by side with per-platform breakdowns
  • Actionable Recommendations — Get prioritized steps to improve your AI visibility
  • MCP Server — Works with Claude Desktop, Cursor, and any MCP-compatible client
  • Consistent Results — Seeded randomness ensures reproducible results for the same brand

MCP Server Installation

Claude Desktop

Add to your claude_desktop_config.json:

json
{  "mcpServers": {    "ai-visibility": {      "command": "npx",      "args": ["-y", "ai-visibility-mcp"]    }  }}

Cursor

Add to your Cursor MCP settings (.cursor/mcp.json):

json
{  "mcpServers": {    "ai-visibility": {      "command": "npx",      "args": ["-y", "ai-visibility-mcp"]    }  }}

npx (standalone)

bash
npx ai-visibility-mcp

MCP Tools

ToolDescription
check_brand_visibilityCheck a brand's visibility across AI platforms with detailed per-platform results, mention rates, positions, sentiment, and competitor analysis
check_single_queryCheck brand mention for a specific query on a specific platform — get mention status, position, context snippet, and sentiment
get_visibility_scoreCalculate overall AI visibility score (0-100) with tier rating, per-platform breakdowns, and improvement recommendations
compare_brandsCompare visibility of 2-10 brands side by side with ranked results and per-platform scores
get_recommendationsGet prioritized, actionable recommendations to improve AI visibility based on current score
list_platformsList all supported AI platforms with details on how each sources and presents brand information

How Scoring Works

The visibility score (0-100) is calculated from three components:

ComponentWeightWhat It Measures
Mention Rate40%How often the brand appears in AI responses
Position Quality30%Where the brand is mentioned (1st = best, 5th = worst)
Sentiment30%Whether mentions are positive, neutral, or negative

Score Tiers:

  • 80-100 Excellent — Strong presence across platforms
  • 60-79 Good — Visible but room to improve
  • 40-59 Moderate — Appears in some responses
  • 20-39 Low — Limited visibility
  • 0-19 Very Low — Rarely mentioned

Self-Hosting

Clone the repo and build the MCP server:

bash
git clone https://github.com/sharozdawa/ai-visibility.gitcd ai-visibility/mcp-servernpm installnpm run build

Run the MCP server directly:

bash
node dist/index.js

Or point your MCP client to the local build:

json
{  "mcpServers": {    "ai-visibility": {      "command": "node",      "args": ["/path/to/ai-visibility/mcp-server/dist/index.js"]    }  }}

Run the Web Dashboard

The project includes a Next.js dashboard for visual tracking:

bash
cd ai-visibilitycp .env.example .env# Set your DATABASE_URL in .envnpm installnpx prisma db pushnpm run dev

Platforms Tracked

PlatformCompanyHow It Sources Information
ChatGPTOpenAITrained on web data; optional web browsing for real-time info
PerplexityPerplexity AIReal-time web search with source citations
ClaudeAnthropicTrained on web data; focuses on accurate, well-reasoned responses
GeminiGoogleLeverages Google Search index and Knowledge Graph

Why AI Visibility vs Paid Alternatives

Featureai-visibilityOtterlyAthenaHQ
Platforms tracked432
Visibility scoreYesYesYes
Competitor analysisYesYesLimited
Sentiment analysisYesNoNo
Self-hostableYesNoNo
Open sourceYesNoNo
PriceFree$100-300/mo$200-500/mo

More Open Source SEO Tools

ToolDescription
awesome-seo-mcp-serversCurated list of SEO MCP servers and agent skills
robotstxt-aiVisual robots.txt manager for AI crawlers
indexnow-mcpInstant URL indexing via IndexNow
schema-genSchema.org JSON-LD markup generator

License

MIT

Built by Sharoz Dawa
[GitHub]

[圖片]

來源：README.md，提交 ba0253d

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包，因此其工具未知。

版本歷史

1
  1. v1.0.0最新Sep 16, 2026

評分

已滿足適用檢查項的 50%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手；SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭，或保持端點能夠回應探測，以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list，或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分