statistics-engine Connector for AI agents.
5 live capabilities
Get 100% accurate math and data analysis on your local datasets.
Waiting for input…
Why people use statistics-engine
Statistics Engine for Accurate Data Analysis
With the Statistics Engine, you just hand your data to your agent and ask for the numbers. It uses a local JavaScript core to crunch the math instantly, giving you the exact mean, median, or standard deviation every single time. You get the speed of an AI with the reliability of a hardcoded calculator.
What Vinkius changes
You get deterministic math results without the risk of LLM hallucinations.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Server Performance Monitoring
An engineer asks for the p95 latency of a 1,000-item log.
- Real-world use case 02
Private Financial Auditing
A researcher wants the standard deviation of a private portfolio.
- Real-world use case 03
Survey Data Analysis
A marketer has a list of ratings and wants the median.
Complete set · 5capabilities
The complete statistics-engine capability set.
These are the exact actions your AI can choose when you ask it to work with statistics-engine.
01—03
3 capabilities in this set.
Part of 5 available through statistics-engine.
- 01 Capability
Calculate standard deviation
Computes the population standard deviation. Use this to see how much your data varies from the average.
- 02 Capability
Calculate percentile
Finds the k-th percentile of your data. It is perfect for understanding distribution tails like p95 or p99.
- 03 Capability
Calculate mean
Calculates the basic mathematical average of a dataset. It gives you a reliable center point for any list of numbers.
04—05
2 capabilities in this set.
Part of 5 available through statistics-engine.
- 04 Capability
Calculate median
Identifies the middle value in your data. This is useful when you need a measure of center that isn't skewed by outliers.
- 05 Capability
Calculate mode
Returns the most frequent value in a dataset. Use this to find the most common occurrence in your data points.
Set up in minutes
One URL. Then ask statistics-engine to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use statistics-engine 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_QakrWZnAdyFSWCuuV9nOWewpJCSEHshlpKJYL6eE/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 statistics-engine, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable statistics-engine for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_QakrWZnAdyFSWCuuV9nOWewpJCSEHshlpKJYL6eE/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 statistics-engine URL.
- Step 03
Save and start
Save the connection and enable statistics-engine in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"statistics-engine": {
"url": "https://edge.vinkius.com/vk_preview_QakrWZnAdyFSWCuuV9nOWewpJCSEHshlpKJYL6eE/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 statistics-engine
Open Agent mode in chat and ask: "Using statistics-engine, help me...". 5 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"statistics-engine": {
"url": "https://edge.vinkius.com/vk_preview_QakrWZnAdyFSWCuuV9nOWewpJCSEHshlpKJYL6eE/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 statistics-engine
Ask Copilot: "Using statistics-engine, help me...". 5 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"statistics-engine": {
"url": "https://edge.vinkius.com/vk_preview_QakrWZnAdyFSWCuuV9nOWewpJCSEHshlpKJYL6eE/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 statistics-engine
Open Cascade and ask: "Using statistics-engine, help me...". 5 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"statistics-engine": {
"url": "https://edge.vinkius.com/vk_preview_QakrWZnAdyFSWCuuV9nOWewpJCSEHshlpKJYL6eE/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 statistics-engine
Ask Cline: "Using statistics-engine, help me...". 5 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add statistics-engine --transport http "https://edge.vinkius.com/vk_preview_QakrWZnAdyFSWCuuV9nOWewpJCSEHshlpKJYL6eE/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 statistics-engine
Ask Claude: "Using statistics-engine, show me...". 5 tools are ready
Where the request belongs
Work statistics-engine can move forward.
This is for the data professional who needs perfect numbers. It is for the ops engineer tired of manual calculations and the researcher who cannot risk data leaks.
Data Analyst
They use this to quickly get distributions and averages from messy logs without exporting to Excel.
Ops Engineer
They use it to calculate p95 and p99 latencies on the fly to identify performance spikes.
Financial Researcher
They use it to run standard deviations on private portfolios while keeping the data on their own machine.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsOutlier Detection Engine
Identify statistical anomalies in massive datasets local using deterministic Z-Score and IQR methods. Stop LLMs from guessing which rows are outliers.
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.
Fundamental Math
A deterministic, zero-latency mathematical engine for exact calculations. Safely compute percentages, square roots, factorials, and the rule of three completely local.
T-Test Statistics Engine
Run exact Student's, Welch's, and Paired t-tests local. Get CPU-guaranteed p-values instead of LLM-hallucinated guesses.
Normality Test Engine
Test whether your data is normally distributed using Skewness and Kurtosis analysis local. Essential pre-check before running parametric statistical tests.
DataFrame Aggregator Engine
Perform blazingly fast GroupBy and Aggregations on massive CSVs local. Save millions of AI tokens and get mathematically perfect sums, means, and counts.
Bring your own AI
Change the model, client or framework. Keep statistics-engine 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 statistics-engine.
The practical details behind the request, access and result.
Can the Statistics Engine handle large datasets?
Yes, it processes data arrays locally on your machine, so it can handle large lists of numbers without the limitations of an AI's context window or memory.
Is my data safe with the Statistics Engine?
Your data is completely private. This Connector runs a local JavaScript core, meaning your numbers never leave your computer or get sent to an external server.
Does the Statistics Engine work with Claude or Cursor?
Yes, it works with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.
How accurate are the math results?
They are 100% mathematically certain. Because it uses a dedicated computational core rather than an LLM's word prediction, the results for mean, median, and standard deviation are always correct.
Can I use this for server performance monitoring?
It is perfect for that. You can ask your agent to calculate p95 or p99 latencies from your logs to identify performance bottlenecks accurately.
What kind of math can the Statistics Engine do?
It covers the core essentials: mean, median, mode, standard deviation, and k-th percentiles.
Why use this instead of asking the AI to analyze the dataset directly?
AIs hallucinate complex data calculations because they generate text, not numbers. This Connector provides the AI with a deterministic capability, forcing it to offload the actual number-crunching to a strict JavaScript engine.
Is my data sent to any external service?
No. The entire engine runs completely local in your local environment. It is "Privacy First" by design, requiring no external APIs or network access.
How does the percentile calculation work?
The capability sorts your dataset and uses a robust interpolation method to find the exact boundary value below which a given percentage of observations fall. Perfect for p95 or p99 SLA reporting.
One connection away
Give your agent a direct line to statistics-engine.
Connect statistics-engine once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available