Number crunch
Statistical analysis suite: descriptive statistics, correlation analysis, and outlier detection on a single dataset.
3 tools run server-side in one request. You pay once, settle once, and get a single response - no orchestration, no per-step payments, and a partial-success envelope if any step fails. USDC over x402 on any supported chain.
When to use this pack
An agent has a series of numbers (prices, scores, measurements) and needs the full statistical picture in one call: central tendency, spread, whether any values are anomalous, and the trend direction.
Tools in this pack
All 3 run inside the single $0.003 call above. Each is also callable on its own if you only need one part.
- Stats summary POST /api/stats-summary Compute the full descriptive-stats panel for an array of numbers in one call: count, sum, mean, median, mode, stddev (sample), variance, min, max, range, q1, q3, IQR. Beats calling 12 separate tools when you already have the array in front of you.
- Correlation (Pearson) POST /api/correlation Pearson correlation coefficient between two equal-length numeric series. Returns r (the correlation, -1 to 1), r² (variance explained), n (sample size). Use this to ask things like: is a stock's daily return correlated with a macro indicator? Are two FRED series moving together?
- Outlier detection (IQR + z-score) POST /api/outliers Flag outliers in a numeric series using either the IQR rule (Tukey fences at 1.5·IQR - robust, default) or z-score (|z| > threshold - assumes normality). Returns the outlier values + their indices + the thresholds used so you can decide whether to trust them.
Bought one at a time, these 3 tools cost $0.003 together; the pack is that sum less a 10% bundle discount, rounded up to the $0.001 settlement floor, which is $0.003.
Workflow
- Compute descriptive statistics with stats-summary - count, mean, median, stddev, quartiles, min, max.
- Run correlation of the values against their indices (position trend) - r near +1/-1 means a clear upward/downward trend over the series.
- Detect outliers - IQR fence + z-score methods flag anomalous values the agent should investigate or exclude.
Arguments
| Name | Required | Description | Example |
|---|---|---|---|
values | yes | Comma-separated numbers (e.g. 10,12,15,11,50,13,14) | 10,12,15,11,50,13,14 |
What one call returns
A JSON object with pack, args, steps, summary; steps holds one entry per tool (stats-summary, correlation, outliers), each with its own result or error. Full example on the API page.
Call it directly
Any x402 client pays the 402 and gets the whole workflow back in one response. With the agent402-client SDK (npm i agent402-client, an ES module):
import { Agent402 } from "agent402-client";
// payFetch: an x402-wrapped fetch your wallet signs (@x402/fetch).
// Tools on the free tier need no options: new Agent402() pays them by proof-of-work.
// an existing prepaid credits key also works: new Agent402({ creditsKey })
const client = new Agent402({ fetch: payFetch });
const result = await client.call("skill-number-crunch", {"values":"10,12,15,11,50,13,14"});
Run it in Claude
claude mcp add agent402 -s user -- npx -y agent402-mcp@latest
Then paste this prompt into Claude:
Analyze the dataset [10,12,15,11,50,13,14] using Agent402: (1) stats-summary - descriptive stats. (2) correlation with x=values, y=indices - trend detection. (3) outliers - flag anomalies. Return {stats, trend, outliers}.