An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect AI Feature Discovery Analytics to ChatGPT and Claude

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. Pinpoint friction points and accelerate user engagement.

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 AI Feature Discovery Analytics.

  1. 01

    Calculate discovery metrics

    Provides the fundamental health score of an AI feature's launch

  2. 02

    Analyze discovery velocity

    Measures the speed of adoption and identifies delays in feature awareness

  3. 03

    Evaluate channel performance

    Determines which marketing or UI paths are most successful at driving engagement

  4. 04

    Generate acceleration strategy

    Provides actionable advice to improve discovery based on current performance gaps

Real work

What teams actually run

01

Post-Launch Performance Review

You just launched a major AI widget. Use this MCP to calculate the discovery metrics and see if the rollout was successful.

02

Onboarding Flow Optimization

The new feature isn't being used. Use the MCP to evaluate your onboarding paths and find the best way to introduce the capability.

03

Marketing Campaign Audit

A specific marketing campaign ran for a month. Use the MCP to compare its performance against your standard channels to prove ROI.

04

Identifying User Drop-off

You suspect users are getting lost between the main dashboard and the new feature. Use the MCP to analyze the discovery velocity and pinpoint the delay.

One connector, every AI

AI Feature Discovery Analytics 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 AI Feature Discovery Analytics 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

899ms average. Fast in production.

AI Feature Discovery Analytics is checked daily against the live service.

Daily averagePeak 1073ms
Oct 3Today
Fastest day
631ms
Slowest day
1073ms
14-day trend
Slowing+8%

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 Feature Discovery Analytics, so you can see the experience inside your AI.

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

AI Feature Discovery Analytics Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_M2ugyR0bdwPEifqVrgkiN2rOjMAmxmSaK4RbYzhA/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 Feature Discovery Analytics capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "ai-feature-discovery-analytics-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_M2ugyR0bdwPEifqVrgkiN2rOjMAmxmSaK4RbYzhA/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 Feature Discovery Analytics in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work AI Feature Discovery Analytics owners hand off.

Product Managers, UX Designers, and Marketing Analysts use this MCP to move beyond gut feelings about feature adoption. Instead of relying on anecdotal feedback, you get concrete data showing exactly where users are getting lost or discouraged. It helps you prove ROI on your product improvements.

  • 01

    Product Manager

    You use this to calculate the core discovery metrics and determine if a new feature is meeting adoption targets.

  • 02

    UX Designer

    You use it to analyze which UI placements cause friction, allowing you to redesign the user flow for better visibility.

  • 03

    Marketing Analyst

    You use it to evaluate which marketing channels or onboarding paths are most successful at driving initial user engagement.

FAQ

Questions AI Feature Discovery Analytics owners ask.

  • 01

    Does this MCP work for any type of feature, or just AI features?

    This MCP is specialized for measuring AI features within a SaaS product. It focuses on the unique challenges of user discovery and adoption for advanced, AI-driven capabilities.

  • 02

    What kind of data does the MCP need to run?

    The MCP needs usage data, including metrics like user counts, feature interaction counts, and timestamps. The prompt examples show how to provide this raw data for calculation.

  • 03

    Can I use this to compare different product versions?

    Yes. You can input data from different time periods or product versions to compare performance, helping you see if a change improved the discovery rate.

  • 04

    Is this MCP just a report generator, or does it give advice?

    It does both. After calculating metrics, the MCP can use the generate_acceleration_strategy capability to provide concrete, actionable advice on how to improve adoption.

  • 05

    What is the discovery rate?

    The discovery rate is the percentage of users who successfully identified and attempted to use an AI feature out of the total group exposed to it, calculated via calculate_discovery_metrics.

  • 06

    How can I improve my feature adoption?

    You can use generate_acceleration_strategy to receive specific, actionable advice based on your current discovery rate, UI friction, and promotion intensity.

  • 07

    Can I compare different marketing channels?

    Yes, the evaluate_channel_performance capability allows you to compare the effectiveness of various channels like Modals, Tooltips, or Email.

Explore

More in Product Management

Suggestions

Connect AI Feature Discovery Analytics to Claude, Cursor, ChatGPT & more