Do analytics the Datalyze way, in your AI tools
Connect the Datalyze MCP to Claude, ChatGPT, or Gemini. When you ask about your data, your AI follows Datalyze methods step by step.
Week-4 retention dropped after we shipped the new onboarding. Where do I look first?
Start with the step that changed, not the cohort curve:
- Compare activation by signup week, so you can tell a funnel change from a mix shift.
- Check that the new onboarding still fires the same events your retention metric depends on.
- Split week-4 retention by acquisition channel before you blame the flow.
Analytics questions, answered like a senior analyst would
Will this event schema hold up?
Paste your plan and get naming, property and identity problems flagged before they reach production.
Why don't my channel numbers add up?
Trace where double counting, missing UTMs and identity gaps are bending your attribution.
Which cohort is actually churning?
Get the cuts worth running first, and how to read the result without fooling yourself.
How should we define activation?
Pick a metric that predicts retention, and see how teams at your stage usually define it.
Mixpanel, Amplitude or PostHog?
A straight recommendation for your stage, stack and budget, with the trade-offs spelled out.
What belongs on the weekly dashboard?
Cut a sprawling dashboard down to the handful of charts that drive decisions.
One plan, one price
- Every Datalyze workflow and the full knowledge base
- Works in every app you connect: Claude, ChatGPT, Gemini and coding agents
- One plan with everything in it. No seats, no tiers, no contract.
Questions before you connect
What is an MCP?
The Model Context Protocol is an open standard that lets an AI app such as Claude, ChatGPT or Gemini use outside tools. The Datalyze MCP gives your AI Datalyze's analytics method and knowledge base.
How does it work?
When you ask about your data, your AI asks Datalyze which of eight workflows fits (explain a change, pull a number, find opportunities, reconcile two numbers, audit, plan, judge a result, answer a question), then works through it one step at a time. Each step comes with the method and the relevant playbook sections, cited with links.
Does Datalyze see my data?
No. Your AI runs the queries through your own data connectors. Datalyze only sends the method and the knowledge base, and doesn't keep what your AI reports back between steps.
What does it cost?
$49 a month. Each payment adds a month of access and nothing renews by itself, so you add another month from Billing whenever you need it.
Which apps can I connect?
Claude on the web, desktop and mobile, Claude Code, ChatGPT, Gemini, Cursor, and any other app that supports remote MCP servers. Most connect by signing in to your Datalyze account; coding agents can use your API key instead.