An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Product Usage Engagement Engine to your AI

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn raw user activity into actionable product health insights.

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

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 4 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-04

4 capabilities in this set.

Part of 4 available through Product Usage Engine.

  1. 01

    Generate power user distribution

    This capability breaks your user base into activity tiers to reveal power-user density. It takes a JSON string of per-user active-day arrays as input.

  2. 02

    Analyze retention correlation

    This capability tests whether higher engagement actually correlates with better retention. You pass in engagement metrics and matching retention rates as JSON strings.

  3. 03

    Calculate engagement score

    This capability rolls session depth and feature adoption into a single health metric. You provide average session duration, actions per session, and the feature adoption rate.

  4. 04

    Get stickiness metrics

    This capability computes the DAU/MAU stickiness ratio to show how often monthly users return daily. You just need to supply the daily and monthly active user counts.

Real work

What teams actually run

01

Measuring Product Stickiness

Use the stickiness capability to see how frequently your monthly users return to the app every day.

02

Validating Feature Impact

Check if higher feature adoption rates are actually leading to better retention numbers.

03

Identifying Power Users

Run a distribution analysis to see if your product is becoming more or less reliant on a small group of heavy users.

04

Health Monitoring

Generate a single engagement score to track the overall health of user sessions over time.

One connector, every AI

Product Usage Engine works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Product Usage Engine to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

875ms average. Fast in production.

Product Usage Engine is checked daily against the live service.

Daily averagePeak 1009ms
Oct 3Today
Fastest day
787ms
Slowest day
1009ms
14-day trend
Slowing+6%

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 Product Usage Engine, so you can see the experience inside your AI.

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

Product Usage Engine Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_IMtyKtVdvlYPnnZKaSgD803v7RS5yLMjhQH0E1pI/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 — Product Usage Engine capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "product-usage-engagement-engine-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_IMtyKtVdvlYPnnZKaSgD803v7RS5yLMjhQH0E1pI/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

Guided setup for Claude? Set up Product Usage Engine in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Product Usage Engine owners hand off.

Product professionals who need to move from raw data to strategic insights without manual math.

  • 01

    Product Managers

    They hand off raw usage data to the AI to get instant health reports.

  • 02

    Data Analysts

    They use the MCP to run quick correlation tests and distribution checks.

  • 03

    Growth Leads

    They use it to measure how feature adoption impacts user retention.

FAQ

Questions Product Usage Engine owners ask.

  • 01

    What is a stickiness ratio?

    It is the ratio of Daily Active Users to Monthly Active Users. It shows how often your monthly users return to your product on a daily basis.

  • 02

    How does the engagement score work?

    The capability takes session duration, the number of actions per session, and the feature adoption rate to create a single synthesized score.

  • 03

    Can I use this with Claude or Cursor?

    Yes, you can connect this MCP to any MCP-compatible client including Claude, Cursor, and Windsurf.

  • 04

    How do I identify power users?

    You use the generate_power_user_distribution capability by passing in a JSON string of user activity days to see how users are distributed across activity tiers.

  • 05

    Does this MCP host my data?

    No, Vinkius hosts the MCP itself, but you provide the specific metrics or data strings to the capabilities when you prompt your agent.

  • 06

    How do I calculate my product's stickiness?

    You can use the get_stickiness_metrics capability by providing your Daily Active Users (DAU) and Monthly Active Users (MAU).

  • 07

    Can I identify my power users?

    Yes, the generate_power_user_distribution capability provides a breakdown of activity levels and identifies the ratio of power users within a 30-day window.

  • 08

    How is the engagement score determined?

    The calculate_engagement_score capability synthesizes session duration, action density, and feature adoption rates into a single score.

Explore

More in Product Management

Suggestions

Connect Product Usage Engine to Claude, Cursor, ChatGPT & more