Does this MCP track all user activity?

No, it focuses specifically on AI feature engagement. It helps you measure how users interact with your AI capabilities, providing metrics on adoption and value realization.

Can I use this for multiple product lines?

The MCP is designed to analyze AI feature engagement. You must ensure the data source feeding the MCP covers all the AI features you want to measure.

What is the difference between engagement and adoption?

Adoption metrics show if users are finding and trying a feature. Engagement scores give a holistic view of how valuable and active the user is with the product overall.

Is this only for large companies?

No. This MCP helps any product team that needs to understand user retention and feature stickiness, regardless of company size.

How is the engagement score calculated?

The score is determined by calculate_user_engagement_score, which evaluates session volume, feature breadth, and the ratio of successful value realizations to total AI outputs.

Can I predict which users might stop using AI features?

Yes, you can use predict_user_churn_risk to identify users showing declining engagement trends and low value realization.

How do I measure if a new AI feature is successful?

Use get_feature_adoption_metrics to compare the discovery rate against the realization rate, which measures how many users actually find value in the feature.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect AI Engagement Scoring to ChatGPT, Claude and Gemini

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. Stop guessing about user retention and product health.

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.

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.

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 AI Engagement Scoring.

01
Calculate user engagement score
Determines a single, current engagement score for a specific user, giving you an immediate health check on their account.
02
Get feature adoption metrics
Evaluates how successfully specific AI features are being discovered by users and how often they are actually adopted.
03
Predict user churn risk
Identifies which users are most likely to abandon your AI features, allowing you to intervene before they leave.
04
Analyze engagement trend
Tracks how a user's interest in your AI features changes over time, showing you if their usage is trending up or down.

Real work

What teams actually run

Reviewing a dormant user

You check a user who hasn't logged in for weeks. The MCP predicts their churn risk and tells you if they were previously a high-value user.

Launching a new feature

You run a report to see if the new feature is being discovered and adopted. The MCP gives you the specific metrics needed to judge success.

Identifying product friction

You notice a drop in usage. The MCP analyzes engagement trends to see if the decline started after a specific product update.

Segmenting power users

You calculate the engagement score for your top 100 users to confirm they are still realizing high value from the AI capabilities.

One connector, every AI

AI Engagement Scoring 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.

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

You don't need a client to put AI Engagement Scoring 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

901ms average. Fast in production.

AI Engagement Scoring is checked daily against the live service.

Daily averagePeak 1215ms

Oct 3Today

Fastest day: 693ms
Slowest day: 1215ms
14-day trend: Slowing+41%

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 Engagement Scoring, so you can see the experience inside your AI.

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

AI Engagement Scoring Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_4wOGVgGo4t204rkw2C4D4i8XjePsZ299pNnX5ev6/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — AI Engagement Scoring capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "ai-engagement-scoring-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_4wOGVgGo4t204rkw2C4D4i8XjePsZ299pNnX5ev6/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 AI Engagement Scoring in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work AI Engagement Scoring owners hand off.

Product Managers and Growth Marketers use this MCP to move beyond vanity metrics. They need to know if users are actually finding value in the AI features, not just clicking around. This capability helps you prioritize product improvements based on real retention risk.

01
Product Manager
Determines which features need immediate attention by analyzing adoption metrics and identifying low-value user segments.
02
Growth Marketer
Builds targeted retention campaigns by flagging users with high churn risk and declining engagement trends.
03
Data Analyst
Generates deep insights into user behavior, comparing discovery rates against actual value realization.

FAQ

Questions AI Engagement Scoring owners ask.

01
Does this MCP track all user activity?
No, it focuses specifically on AI feature engagement. It helps you measure how users interact with your AI capabilities, providing metrics on adoption and value realization.
02
Can I use this for multiple product lines?
The MCP is designed to analyze AI feature engagement. You must ensure the data source feeding the MCP covers all the AI features you want to measure.
03
What is the difference between engagement and adoption?
Adoption metrics show if users are finding and trying a feature. Engagement scores give a holistic view of how valuable and active the user is with the product overall.
04
Is this only for large companies?
No. This MCP helps any product team that needs to understand user retention and feature stickiness, regardless of company size.
05
How is the engagement score calculated?
The score is determined by calculate_user_engagement_score, which evaluates session volume, feature breadth, and the ratio of successful value realizations to total AI outputs.
06
Can I predict which users might stop using AI features?
Yes, you can use predict_user_churn_risk to identify users showing declining engagement trends and low value realization.
07
How do I measure if a new AI feature is successful?
Use get_feature_adoption_metrics to compare the discovery rate against the realization rate, which measures how many users actually find value in the feature.

Explore

More in Analytics

Connect AI Engagement Scoring to Claude, Cursor, ChatGPT & more

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

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Calculate user engagement score

Get feature adoption metrics

Predict user churn risk

Analyze engagement trend

What teams actually run

Reviewing a dormant user

Launching a new feature

Identifying product friction

Segmenting power users

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

AI Engagement Scoring Connector

Claude Desktop

Product Manager

Growth Marketer

Data Analyst

Does this MCP track all user activity?

Can I use this for multiple product lines?

What is the difference between engagement and adoption?

Is this only for large companies?

How is the engagement score calculated?

Can I predict which users might stop using AI features?

How do I measure if a new AI feature is successful?

AI Feature Adoption Analytics AI Connector

Enterprise User Adoption Analytics AI Connector

Enterprise Email Engagement Analytics AI Connector

Churn Rate Calculator AI Connector

Suggestions

ChurnZero AI Connector

Twitter CTA and Engagement Scorer AI Connector

Feature Adoption Analytics AI Connector

Dune Analytics (Web3 SQL Analytics API) AI Connector