GrackerAI

ai.gracker由 gracker.ai 發布官方發布者v1.0.0更新於 Nov 3, 2026

See how ChatGPT, Perplexity, Gemini and Google AI Overviews mention and cite your brand.

已驗證Streamable HTTP可網頁執行AI 與機器學習

概覽

GrackerAI 的託管 MCP 服務（portal.gracker.ai），由 gracker.ai 發布；需要 OAuth 登入；Streamable HTTP。

暫無 AI 概覽：以下資訊來自註冊中心條目和服務本身。

發布者
gracker.ai
端點
portal.gracker.ai
最近檢查

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 GrackerAI，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.gracker%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": {
    "grackerai": {
      "type": "http",
      "url": "https://portal.gracker.ai/mcp"
    }
  }
}

README

GrackerAI MCP Server

Bring your AI visibility data into Claude, ChatGPT, Cursor, and any other MCP client.

GrackerAI tracks how AI engines (ChatGPT, Perplexity, Gemini, Copilot, Grok, and Google AI Overviews) talk about your brand. With this MCP server, your AI assistant can query that data live. You don't need to export reports or copy numbers into a chat.

This is a hosted (remote) MCP server. There is nothing to install or run. Add the URL below to your client and sign in with your GrackerAI account.

https://portal.gracker.ai/mcp

Setup

Chat apps

ClientWhere to add it
ClaudeSettings → Connectors → Add custom connector → paste the URL
ChatGPTSettings → Connectors → Add custom connector → paste the URL
CopilotSettings → Connectors → Add custom connector → paste the URL
GeminiExtensions → Add custom MCP server → paste the URL
GrokConnectors → Add custom connector → paste the URL
PerplexitySettings → Connectors → Add custom connector → paste the URL

Cursor

.cursor/mcp.json:

json
{  "mcpServers": {    "gracker": {      "url": "https://portal.gracker.ai/mcp"    }  }}

VS Code

.vscode/mcp.json:

json
{  "servers": {    "gracker": {      "type": "http",      "url": "https://portal.gracker.ai/mcp"    }  }}

Claude Code

bash
claude mcp add --transport http gracker https://portal.gracker.ai/mcp

Any other MCP client works the same way: add the URL in its server settings.

First connection

A browser window opens so you can log in to GrackerAI. Next, pick which brands this connection can access. All brands start selected, and your assistant only sees the brands you leave selected. To disconnect, remove the connector from your AI client.

Tools

ToolWhat it does
get_visibility_schemaReturns the shape of your AI visibility data (types and fields). Your assistant reads this first.
query_visibility_dataRuns a read-only query against your data. Results are always limited to the brands you authorized.

What you can ask

You don't need to learn a query language. Ask in plain words and your assistant writes the query.

  • "What's my visibility score for the last 7 days? Break it down by engine."
  • "Which tracked prompts had zero mentions of my brand in the last 60 days?"
  • "Show negative mentions of my brand this month, with the engine and the prompt that triggered each."
  • "Which competitors show up most often in answers where I'm missing?"
  • "Which domains do AI answers cite most for my category prompts?"

Data covered

  • Visibility: score, presence, and mention counts by prompt, engine, country, and date range
  • Mentions: each time a brand is named, with position, prominence, sentiment, and whether the claim was accurate
  • Citations: each URL an AI answer cited, with domain, source type, publish date, and whether it supported the claim
  • Competitors: the competitors you track plus brands AI engines compare you with
  • Prompts: your tracked prompts and their results, with intent and funnel stage

Requirements

You need a GrackerAI account with at least one brand set up. Start here.

Support

Questions or problems: open an issue in this repo or see the docs.

來源：README.md，提交 d0a4625

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

1
  1. v1.0.0最新Nov 3, 2026

評分

已滿足適用檢查項的 75%

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

    請在儲存庫或註冊中心條目中宣告授權條款。