AIMentionTracker

ai.aimentiontracker由 aimentiontracker.ai 發布官方發布者v0.1.3更新於 Oct 24, 2026

How often ChatGPT, Claude, Gemini and Perplexity name and cite your brand, with the evidence.

已驗證Streamable HTTP可網頁執行資料與分析商業與電商

概覽

AI 產生的概覽

AIMentionTracker 是唯讀的 MCP 伺服器，用來查看 ChatGPT、Claude、Gemini、Perplexity 等 AI 助理提及並引用你品牌的頻率。

可以做什麼
查詢金鑰身分、方案與回報門檻，並取得目前 UTC 日期及各工具回溯的時間範圍。列出工作區追蹤的品牌與問題，以及每個問題產生的答案數量。依引擎與品牌讀取 AI 能見度、聲量佔比與情感計數。查看被提及的競爭對手、含提及與引用的已存答案，以及引擎回答前閱讀的網域。檢視提醒與排序後的建議，並在啟用整合時讀取 Search Console 資料。
適用情境
當你需要衡量或說明品牌在 AI 生成答案中的出現情況（答案引擎優化）並與競爭對手比較時，或需要查看這些數字背後真實答案與來源作為依據時使用。
執行需求
可使用託管的遠端端點並以 OAuth 持有者權杖驗證，或透過 npx 執行本機 npm 套件，後者需要 Node.js 與 AMT_API_KEY 環境變數。API 金鑰在 AIMentionTracker 應用程式中建立，且僅限單一組織。
安裝前請注意
API 金鑰是機密，透過 Authorization 標頭或 AMT_API_KEY 傳遞，請妥善保管。存取為唯讀，無法變更帳單、團隊或追蹤內容，伺服器本身不保存機密。答案過少時數值可能為空，各引擎分別回報而不取平均。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 AIMentionTracker，將其新增到工作區。
  2. 連接 所需的 憑證。它們會被私密儲存，絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/ai.aimentiontracker%2Fmcp/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。 客戶端會在首次連接時完成 OAuth 登入。

{
  "mcpServers": {
    "aimentiontracker": {
      "type": "http",
      "url": "https://mcp.aimentiontracker.ai/mcp"
    }
  }
}

README

@aimentiontracker/mcp

Track how often ChatGPT, Claude, Gemini, Perplexity and Google AI Overviews name and cite your brand, from inside your MCP client. Twelve read-only tools over AI visibility, share of voice, sentiment, competitor mentions and what to do about them, with the answers they came from.

This is answer engine optimisation (AEO) data, not rank tracking: the unit is an answer an assistant gave a real question, and whether you were in it.

Hosted (no install)

bash
claude mcp add --transport http aimentiontracker https://mcp.aimentiontracker.ai \  --header "Authorization: Bearer amt_live_YOUR_KEY"

Local (stdio)

bash
claude mcp add aimentiontracker -e AMT_API_KEY=amt_live_... -- npx -y @aimentiontracker/mcp

Create a key at app.aimentiontracker.ai/api-keys. Keys are read-only and scoped to one organisation; they cannot change billing, the team, or what is tracked.

Tools

All read-only. v1 has no write endpoints, deliberately: adding a prompt expands a metered bill and triggering a run spends real vendor money.

ToolWhat it answers
get_meWho this key is, the plan, and the reporting thresholds. Call first.
get_current_dateToday in UTC, and the trailing windows every other tool counts back from. Call before reasoning about dates.
list_brandsWhich brands this key can read, and their ids
list_questionsThe questions this workspace runs, and how many answers each produced. Call before reading a disappointing number: it may be the wrong question, not poor visibility
get_visibilityPresence per engine and per brand over a window
get_share_of_voiceEach tracked brand's mentions as a share of the tracked set
get_sentimentRecommended, negative and neutral counts per brand, against the classified denominator
list_competitorsWho gets named instead of you, including answers that named them and never mentioned you
list_answersThe stored answers, with mentions and citations
list_sourcesDomains the engines read before answering
list_alertsFindings worth acting on
list_recommendationsWhat to do next, ranked, with the pages and answers behind each item. Check displayable: false means the corpus is too thin to rank, not that there is nothing to do

One further tool, list_search_console, registers only where the Google Search Console integration is enabled. A tool that always answers 404 is worse than an absent one: an agent picks it for a task it cannot do and spends a turn failing.

Three rules the tools enforce

  1. A null rate means "not enough answers yet", never zero. Rendering it as 0% reports a collapse that did not happen.
  2. Engines are never averaged. They disagree; a mean describes no real surface.
  3. An empty findings list does not mean nothing changed. list_alerts says so in the payload, not just the description.

Every tool that reports a measurement carries these rules in its own description, because an agent reads the tool, not the README.

Why the denominators are in the payload

get_share_of_voice returns brands_counted, and get_sentiment counts against classified rather than total mentions. A workspace tracking two competitors and one tracking twelve produce incomparable shares from identical answers, and the sentiment classifier abstains on listicle mentions where an engine named a brand without endorsing it. Both numbers are meaningless without the denominator beside them, so the tools return it rather than trusting the caller to ask.

Security

The hosted server holds no secrets. No database, no vendor credentials, no service account. Your key arrives in the Authorization header and is passed straight through to the API, which does all authentication, tenancy, entitlement and rate limiting. Each request gets a fresh, stateless server instance that is closed when the response ends.

More

MIT.

來源：README.md，提交 5d14262

工具

0
該伺服器需要登入，因此 SourceWeft 無法在沒有帳號的情況下讀取其工具，也未收錄。已連接帳號所能看到的內容可能因帳號及其權限而異。

版本歷史

2
  1. v0.1.3最新Oct 9, 2026
  2. v0.1.2Oct 1, 2026

評分

已滿足適用檢查項的 85%

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 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 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