Download PDFMarkdown Version
ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use AI Model Usage Analytics with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Know exactly where every dollar of compute goes.

Included with plan

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Complete set · 4 capabilities

The complete AI Model Usage Analytics capability set.

These are the exact actions your AI can choose when you ask it to work with AI Model Usage Analytics.

Capability set01 / 01

01-04

4 capabilities in this set.

Part of 4 available through AI Model Usage Analytics.

  1. 01

    Get feature cost breakdown

    To determine the exact monetary expenditure for each individual product feature

  2. 02

    Get routing efficiency score

    To evaluate how effectively the system is selecting models for specific feature tasks

  3. 03

    Identify optimization targets

    To find features where costs are high but user engagement is low, or where model selection appears inefficient

  4. 04

    Analyze usage concentration

    To identify which features are the primary drivers of AI model consumption

Observed, not estimated

842ms average. Fast in production.

AI Model Usage Analytics is checked daily against the live service.

Daily averagePeak 959ms
Aug 28Today
Fastest day
684ms
Slowest day
959ms
14-day trend
Slowing+14%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 4 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of AI Model Usage Analytics, so you can see the experience inside your AI.

It does not authenticate your account with AI Model Usage Analytics. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

AI Model Usage Analytics Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_1tbd24ReYBC3SDpWJ579WdByT3lsZc0AwncKcSyG/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — AI Model Usage Analytics capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "ai-model-usage-analytics-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_1tbd24ReYBC3SDpWJ579WdByT3lsZc0AwncKcSyG/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Who it's for

Built for the work AI Model Usage Analytics owners hand off.

This MCP is essential for anyone managing a product that uses AI models. If you need to justify AI spending, track costs by feature, or find ways to cut compute expenses, this is for you. It gives you the data to talk to engineering and finance.

  • 01

    Product Manager

    Uses this to understand which features are driving the most usage and cost, helping prioritize development.

  • 02

    Engineering Lead

    Uses this to pinpoint inefficient model usage and identify technical areas that need optimization.

  • 03

    FinOps Analyst

    Uses this to calculate precise cost attribution per feature, making budget reports accurate.

FAQ

Questions AI Model Usage Analytics owners ask.

  • 01

    Does this MCP track costs for every single AI model I use?

    Yes. This MCP provides deep visibility into how AI model resources are consumed across your product, allowing you to calculate cost attribution per feature.

  • 02

    What is the difference between usage concentration and cost breakdown?

    Usage concentration tells you which features are the primary drivers of overall AI model calls. The cost breakdown gives you the exact monetary expenditure for each individual feature.

  • 03

    Can I use this with my existing AI stack?

    Since this MCP is hosted on Vinkius, you connect your preferred AI client—like Claude, Cursor, or Windsurf—once, and you get access to all the analytics capabilities.

  • 04

    Is this only for cost tracking, or can it help with efficiency?

    It does both. You can find cost-saving opportunities by identifying optimization targets, or you can evaluate model selection effectiveness using the routing efficiency score.

Explore

More in Analytics

Suggestions