Test Duration Calculator Connector for AI agents.
3 live capabilities
Plan A/B test sample sizes and experiment timelines with statistical accuracy.
Waiting for input…
Why people use Test Duration Calculator
Test Duration Calculator A/B Test Statistical Planning
This Connector changes that by letting you just tell your agent what you want to achieve. You give it your goals, and it spits out the hard numbers for sample sizes and calendar dates. You get a clear plan to show your team instead of a bunch of confusing formulas.
What Vinkius changes
You get a concrete, data-backed timeline for your A/B tests instead of just guessing.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 6,100+ Connectors
- Real-world use case 01
Verifying detectable lift
A growth lead needs to know if a 2% lift is detectable.
- Real-world use case 02
Roadmap planning
A product manager wants to know if a test will take a month.
- Real-world use case 03
Risk assessment
An analyst is worried about a long-running test.
Complete set · 3capabilities
The complete Test Duration Calculator capability set.
These are the exact actions your AI can choose when you ask it to work with Test Duration Calculator.
01—03
3 capabilities in this set.
Part of 3 available through Test Duration Calculator.
- 01 Capability
Calculate sample size
Determine the exact number of users needed per variant to reach your desired statistical power. This helps you avoid underpowered tests.
- 02 Capability
Estimate timeline
Convert sample size requirements into a calendar view that accounts for daily traffic and weekly cycles. It helps you plan your launch dates.
- 03 Capability
Get finalization details
Project your final experiment end date and get a warning if the test duration poses a high risk of bias. Use this to avoid 'zombie' experiments.
Set up in minutes
One URL. Then ask Test Duration Calculator to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Test Duration Calculator from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_O1AMvmlC1UbiIg5EToBCmgYLv4CFNyrsTcP8VO1g/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Test Duration Calculator, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Test Duration Calculator for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_O1AMvmlC1UbiIg5EToBCmgYLv4CFNyrsTcP8VO1g/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Test Duration Calculator URL.
- Step 03
Save and start
Save the connection and enable Test Duration Calculator in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"test-duration-calculator": {
"url": "https://edge.vinkius.com/vk_preview_O1AMvmlC1UbiIg5EToBCmgYLv4CFNyrsTcP8VO1g/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Test Duration Calculator
Open Agent mode in chat and ask: "Using Test Duration Calculator, help me...". 3 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"test-duration-calculator": {
"url": "https://edge.vinkius.com/vk_preview_O1AMvmlC1UbiIg5EToBCmgYLv4CFNyrsTcP8VO1g/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Test Duration Calculator
Ask Copilot: "Using Test Duration Calculator, help me...". 3 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"test-duration-calculator": {
"url": "https://edge.vinkius.com/vk_preview_O1AMvmlC1UbiIg5EToBCmgYLv4CFNyrsTcP8VO1g/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Test Duration Calculator
Open Cascade and ask: "Using Test Duration Calculator, help me...". 3 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"test-duration-calculator": {
"url": "https://edge.vinkius.com/vk_preview_O1AMvmlC1UbiIg5EToBCmgYLv4CFNyrsTcP8VO1g/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Test Duration Calculator
Ask Cline: "Using Test Duration Calculator, help me...". 3 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add test-duration-calculator --transport http "https://edge.vinkius.com/vk_preview_O1AMvmlC1UbiIg5EToBCmgYLv4CFNyrsTcP8VO1g/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Test Duration Calculator
Ask Claude: "Using Test Duration Calculator, show me...". 3 tools are ready
Where the request belongs
Work Test Duration Calculator can move forward.
This is for growth engineers and data scientists who are tired of manually crunching stats in Excel or over-complicating the math every time a new feature drops.
Growth Engineer
Uses this to tell stakeholders exactly when a new feature will be ready for a full rollout.
Data Scientist
Uses this to ensure every experiment has enough power to be statistically significant before it even starts.
Product Manager
Uses this to manage the roadmap and ensure experiments don't overlap or run indefinitely.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse Connectors
AB Test Sample Size Calculator
Calculate required sample size, test duration, and peeking risk for A/B experiments.
A/B Test Significance Calculator
Calculate statistical significance, required sample sizes, and power for A/B tests.
Bayesian A/B Testing Calculator
Quantify conversion probability, expected loss, and uplift using Bayesian inference.
Multivariate Test Analyzer
Perform 2k factorial analysis to identify optimal element combinations and interaction effects in multivariate experiments.
Feature Flag Rollout Calculator
Calculate deterministic user assignment, rollout projections, and statistical sample sizes for feature flags.
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.
Bring your own AI
Change the model, client or framework. Keep Test Duration Calculator 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 Test Duration Calculator.
The practical details behind the request, access and result.
How does the Test Duration Calculator help with A/B testing?
It tells you exactly how many users you need to see to trust your results. It removes the guesswork from your experiment setup so you don't waste time on tests that won't reach significance.
Can the Test Duration Calculator project my experiment end date?
Yes, it takes your daily traffic and required sample size to give you a specific calendar date. This helps you plan your product roadmap with actual dates instead of vague estimates.
Does the Test Duration Calculator account for weekly trends?
It does. The timeline capability is designed to suggest full weekly cycles to make sure your data isn't skewed by people behaving differently on weekends.
How do I know if my experiment is too long?
You can use the capability to get a risk assessment. It will flag experiments that run long enough to potentially pick up noise from outside your actual test.
Can I use the Test Duration Calculator for multiple variants?
Yes, you can specify how many variants you're testing. The capability will adjust the total sample size needed to ensure each variant has enough data.
What is the difference between sample size and duration?
Sample size is the total number of users you need to see. Duration is how long that will actually take based on your current traffic. This Connector calculates both.
How does the capability handle day-of-week bias?
The capability uses estimate_timeline to round up the required duration to the nearest full 7-day cycle, ensuring that weekly seasonality does not bias your results.
What is considered a high-risk experiment duration?
Any experiment projected to run longer than 4 weeks is flagged as high risk by get_finalization_details due to potential external noise like holidays or marketing changes.
Can I calculate sample size for multiple variants?
Yes, by providing the total number of experimental groups to calculate_sample_size, the capability will determine the cumulative required samples.
One connection away
Give your agent a direct line to Test Duration Calculator.
Connect Test Duration Calculator once. Keep it beside 6,100+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available