AIMentionTracker

ai.aimentiontrackerv0.1.2更新于 Oct 1, 2026

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

已验证Streamable HTTP可网页运行Web Search & Scraping Data & Analytics

概览

AI 生成的概览

让助手读取品牌在 ChatGPT、Claude、Gemini、Perplexity 等 AI 引擎中被提及和引用的频率，以及相关答案与来源。

功能: AIMentionTracker 通过一组只读工具提供品牌的 AI 可见度数据。get_me 返回密钥身份、套餐和报告阈值；list_brands 列出可读取的品牌及其 id；get_visibility 按引擎和品牌给出某时间窗口内的出现情况；list_answers 返回已存储的答案及其提及与引用；list_sources 显示引擎回答前读取的域名；list_alerts 返回值得处理的发现。工具刻意不对各引擎取平均，并把空比率视为数据不足而非零。
适用场景: 当你希望助手回答品牌在 AI 助手回答中的可见度问题，例如哪些引擎提到它、引用了什么、读取了哪些来源时，可以使用它。适合需要原始答案而非单一评分的市场、SEO 和品牌监测工作。
运行要求: 可以使用托管 HTTP 端点 mcp.aimentiontracker.ai 并携带 Authorization Bearer 密钥，也可以通过 npx 以 stdio 方式运行本地 npm 包 @aimentiontracker/mcp。两者都需要在 app.aimentiontracker.ai/api-keys 创建的 API 密钥，本地服务器以 AMT_API_KEY 提供。需要能访问 AIMentionTracker API 的网络。

安装前请注意

API 密钥属于凭据：本地服务器以 AMT_API_KEY 接收，托管服务器以 Authorization Bearer 请求头接收。据说明该密钥为只读，不能更改账单、团队或监测对象。所有工具均为只读；README 指出新增提示词或触发运行会花费真实的供应商费用，因此 v1 没有写入端点。品牌可见度数据会发送到 AIMentionTracker 服务。

安装

在 SourceWeft 中

打开控制台中的 AIMentionTracker，将其添加到工作区。
为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。远程服务在工作区中配置后即可从网页运行时运行。

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

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

README

@aimentiontracker/mcp

MCP server for AIMentionTracker: how often AI assistants name and cite your brand.

Hosted (no install)

bash

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

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

Local (stdio)

Create a key at app.aimentiontracker.ai/api-keys.

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.

Tool	What it answers
`get_me`	Who this key is, the plan, and the reporting thresholds. Call first.
`list_brands`	Which brands this key can read, and their ids
`get_visibility`	Presence per engine and per brand over a window
`list_answers`	The stored answers, with mentions and citations
`list_sources`	Domains the engines read before answering
`list_alerts`	Findings worth acting on

Three rules the tools enforce

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

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.

MIT.

来源：README.md，提交 5a20f49

工具

工具元数据尚未被收录。

版本历史

v0.1.2最新Oct 1, 2026