Skip to content
Vinkius

jstat Connector for AI agents.

1 live capability

Get mathematically exact p-values for A/B testing and hypothesis validation.

Live agent request jstat / Connector

Waiting for input…

AI Agent

Why people use jstat

T-Test Statistics Engine for Accurate Hypothesis Testing

This Connector closes that gap. Your agent handles the data extraction and the math happens instantly in the background. You stay in your chat window and get a definitive answer on whether your results actually matter.

  • Claude
  • ChatGPT
  • Gemini
  • Cursor
  • Visual Studio Code
  • Windsurf

What Vinkius changes

That you get deterministic math results instead of LLM guesses.

Use it from Claude, ChatGPT, Cursor or another AI client you already have.

One account · 6,100+ Connectors

  1. Real-world use case 01

    A/B Testing Significance

    A product manager wants to know if a new UI button actually increased clicks.

  2. Real-world use case 02

    Medical Research Comparison

    A researcher compares blood pressure readings from two groups.

  3. Real-world use case 03

    Manufacturing Quality Control

    A quality control lead checks if a batch of weights deviates from a 500g target.

Complete set · 1capability

The complete jstat capability set.

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

Capability set01 / 01

01

1 capability in this set.

Part of 1 available through jstat.

  1. 01 Capability

    Calculate t test

    Runs independent, paired, or one-sample t-tests to get exact p-values. It ensures your results are mathematically sound by using a local CPU calculation.

Set up in minutes

One URL. Then ask jstat to work.

Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use jstat from the conversation.

Choose your client

Live preview
Advanced clients IDE · CLI

Claude · Web + desktop

Official guide ↗

Connector URL · ready to paste

Streamable HTTP
https://edge.vinkius.com/vk_preview_EmtZwk2XpPdUyFvH15enT6zX1o0mdbBKs430ALWM/mcp
  1. Step 01

    Open Connectors

    In Claude Web or Claude Desktop, open Settings and choose Connectors.

  2. Step 02

    Add the URL

    Choose Add custom connector, name it jstat, and paste the URL above.

  3. Step 03

    Turn it on in chat

    Select +, open Connectors, and enable jstat for the conversation.

Where the request belongs

Work jstat can move forward.

Built around the request

Data scientists, researchers, and analysts who need 100% accuracy in hypothesis testing and can't risk hallucinated p-values in their reports.

01

Data Scientist

Running A/B test significance checks on production data to ensure results aren't just noise.

02

Academic Researcher

Validating experimental results for peer-reviewed papers where precision is a requirement.

03

QA Engineer

Comparing performance metrics between two different software versions to identify real regressions.

Build the capability set

Add more capabilities.

Each Connector adds new actions and data without changing how you work.

Browse Connectors
ANOVA Calculator Engine logo
01 1 capability

ANOVA Calculator Engine

Run exact One-Way ANOVA tests to compare means across multiple groups local. Get CPU-guaranteed F-scores and p-values, not LLM guesses.

View Connector
Chi-Square Test Engine logo
02 1 capability

Chi-Square Test Engine

Run exact Chi-Square independence tests on contingency tables local. Get CPU-guaranteed chi² statistics and p-values for categorical analysis.

View Connector
Normality Test Engine logo
03 1 capability

Normality Test Engine

Test whether your data is normally distributed using Skewness and Kurtosis analysis local. Essential pre-check before running parametric statistical tests.

View Connector
Statistics Engine logo
04 5 capabilities

Statistics Engine

A zero-latency statistical engine to process datasets. Instantly compute the exact mean, median, mode, standard deviation, and percentiles completely local.

View Connector
A/B Test Significance Calculator logo
05 4 capabilities

A/B Test Significance Calculator

Calculate statistical significance, required sample sizes, and power for A/B tests.

View Connector
Data Analysis Prover logo
06 1 capability

Data Analysis Prover

A marketing team asked an AI to analyze campaign data. The AI reported 'significant correlation between email frequency and purchase rate (p<0.05).' The team tripled emails. Unsubscribes spiked 340%. Sample: N=47 self-selected respondents, no power analysis. Correlation: observational, no confounders. Distribution: right-skewed but mean used. p=0.043 but Cohen's d=0.12. trivial. Chart: truncated Y-axis making a 2% difference look enormous. This capability forces five axes: sample validity, causal inference, distribution awareness, significance with effect size, and visualization integrity.

View Connector

Bring your own AI

Change the model, client or framework. Keep jstat connected.

  • Claude
  • ChatGPT
  • Gemini
  • Cursor
  • VS Code
  • Windsurf
  • ZCode
  • Cline
  • Zed
  • Continue
  • Kiro
  • Roo Code
  • Zencoder
  • Goose
  • Void
  • Augment Code
  • Amp
  • Qodo
  • Tabnine
  • Pieces
  • Sourcegraph Cody
  • JetBrains
  • Warp
  • Amazon Q
  • Antigravity
  • BoltAI
  • Raycast
  • Jan
  • LM Studio
  • AnythingLLM
  • Open WebUI
  • Msty
  • Cherry Studio
  • LibreChat
  • TypingMind
  • Chorus
  • 5ire
  • n8n
  • LangChain
  • LlamaIndex
  • CrewAI
  • Vercel AI SDK

Before you connect

Questions about jstat.

The practical details behind the request, access and result.

Can the T-Test Statistics Engine calculate p-values?

Yes, it provides exact p-values calculated by a local engine. This means you get mathematically sound results instead of a guess from your AI client.

Is my data safe with the T-Test Statistics Engine?

Your data stays local. The Connector sends the numbers to a local library on your machine, so your private information never hits a third-party cloud.

What types of t-tests does it support?

It handles independent, paired, and one-sample t-tests. This covers the most common requirements for hypothesis testing in data science.

Can I use it for A/B testing?

It's perfect for A/B testing. You can ask your agent to compare two groups and get a mathematically sound significance check for your variants.

Does it work with my current AI client?

Yes, it works with any MCP-compatible client like Claude or Cursor. You just connect it and start asking for stats.

How accurate are the results?

They are deterministic. Because it uses a CPU-based engine instead of a language model, the math is as accurate as a dedicated statistical capability.

Why shouldn't I just ask the AI to calculate the p-value directly?

Because Large Language Models generate text based on probability, not logic. They frequently hallucinate complex floating-point math. This engine forces the AI to use a real local calculator, producing exact results every single time.

Does it assume equal variances?

For independent tests, it currently uses the standard Student's t-test which assumes equal variance. Paired and one-sample tests calculate their specific formulas independently.

What alpha level is used for significance interpretation?

The engine automatically interprets significance using the standard alpha = 0.05 (95% confidence level). The exact p-value is always returned so you can apply any custom threshold.

One connection away

Give your agent a direct line to jstat.

Connect jstat once. Keep it beside 6,100+ managed Connectors when the next task needs more.

Explore every Connector No credit card required · Free tier available