AIMentionTracker

ai.aimentiontrackerv0.1.2Updated Oct 1, 2026

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

VerifiedStreamable HTTPWeb executableWeb Search & Scraping Data & Analytics

Overview

AI-generated overview

Lets an assistant read how often AI engines such as ChatGPT, Claude, Gemini and Perplexity name and cite a brand, with the supporting answers and sources.

What it does: AIMentionTracker exposes read-only tools over a brand's AI visibility data. get_me identifies the key, plan and reporting thresholds; list_brands lists readable brands and their ids; get_visibility reports presence per engine and brand over a window; list_answers returns stored answers with mentions and citations; list_sources shows domains engines read; list_alerts returns findings worth acting on. The tools deliberately avoid averaging engines and treat a null rate as insufficient data rather than zero.
When to use it: Use it when you want an assistant to answer questions about a brand's visibility in AI assistant answers, such as which engines mention it, what they cite, or which sources they read. It suits marketing, SEO and brand-monitoring work that needs the underlying answers rather than a single score.
Requirements: Either the hosted HTTP endpoint at mcp.aimentiontracker.ai with an Authorization Bearer key, or the local npm package @aimentiontracker/mcp run through npx over stdio. Both need an API key created at app.aimentiontracker.ai/api-keys, supplied as AMT_API_KEY for the local server. Network access to the AIMentionTracker API is required.

Before you install

The API key is a credential: the local server takes it as AMT_API_KEY and the hosted server as an Authorization Bearer header. It is described as read-only and unable to change billing, the team, or what is tracked. All tools are read-only; the README notes that adding prompts or triggering runs would spend real vendor money, which is why v1 has no write endpoints. Brand visibility data is sent to the AIMentionTracker service.

Installation

In SourceWeft

Open AIMentionTracker in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

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

README