Skip to content

BRAINIAC Statistics & Quality Engineering MCP server

software.brainiac/statisticsbrainiac.softwarestreamable-httpv1.0.1Scanned

Paid Statistics & Quality Engineering API via x402. Unpaid tool calls return 402.

15 tools: 14 change things and 1 only read.

Tools: 0 delete, 0 irreversible, 14 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 15
  • Can send data out · 0
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

14 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the BRAINIAC Statistics & Quality Engineering MCP server can do

The BRAINIAC Statistics & Quality Engineering MCP server is published by brainiac.software, a domain the MCP Registry verified. It has 15 tools. It can create or change data (14 tools: statistics_t-test, statistics_anova, statistics_chi-square-test, statistics_nonparametric-tests and 10 more), but cannot delete data. 1 tool only reads.

15 tools bring in text other people can write (statistics_t-test, statistics_anova, statistics_chi-square-test and 12 more).

The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 20, 2026, version 1.0.1.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

15 tools

Changes things 14Claude Code: ask
  • statistics_anovaOne-way and two-way ANOVA with interaction (Type II or III sums of squares), R-squared, Tukey HSD post-hoc comparisons and the Brown-Forsythe (median-centred Levene) test of equal …Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    One-way and two-way ANOVA with interaction (Type II or III sums of squares), R-squared, Tukey HSD post-hoc comparisons and the Brown-Forsythe (median-centred Levene) test of equal variances. Sums of squares use centred two-pass accumulation and match NIST StRD SiRstv. Price $0.03 USDC. POST /api/v1/statistics/anova. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Run one-way or two-way ANOVA
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • statistics_chi-square-testChi-square test of independence (with optional Yates correction), goodness of fit, Fisher's exact test for 2x2 tables and Cramer's V, with expected counts and a low-expected-cell w…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Chi-square test of independence (with optional Yates correction), goodness of fit, Fisher's exact test for 2x2 tables and Cramer's V, with expected counts and a low-expected-cell warning. Price $0.02 USDC. POST /api/v1/statistics/chi-square-test. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Run a chi-square test
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • statistics_control-chartControl limits and Western Electric or Nelson rule violations for I-MR, X-bar R, X-bar S, p, np, c and u charts from caller-supplied measurements or counts, with optional fixed Pha…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Control limits and Western Electric or Nelson rule violations for I-MR, X-bar R, X-bar S, p, np, c and u charts from caller-supplied measurements or counts, with optional fixed Phase II limits. Price $0.04 USDC. POST /api/v1/statistics/control-chart. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Compute control chart limits and violations
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • statistics_doe-design-generateFull and fractional factorial (with defining relation, resolution and alias structure), Plackett-Burman and central composite designs in standard order, optionally randomised with …Reads text others write1 finding

    Why it is in this group

    • The name "statistics_doe-design-generate" says "generate": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The server marks "statistics_doe-design-generate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "statistics_doe-design-generate" says "generate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Full and fractional factorial (with defining relation, resolution and alias structure), Plackett-Burman and central composite designs in standard order, optionally randomised with a seeded xorshift128+ shuffle that is reproducible across languages. Price $0.03 USDC. POST /api/v1/statistics/doe-design-generate. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Generate a designed experiment
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • statistics_gage-rrCrossed gage repeatability and reproducibility by the ANOVA method: variance components, percent contribution, percent study variation, percent tolerance and number of distinct cat…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Crossed gage repeatability and reproducibility by the ANOVA method: variance components, percent contribution, percent study variation, percent tolerance and number of distinct categories for a balanced parts by operators by replicates study. Price $0.05 USDC. POST /api/v1/statistics/gage-rr. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Run a crossed gage R&R study
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • statistics_linear-regressionOrdinary least squares by Householder QR with coefficient standard errors, t-tests and intervals, R-squared, F, VIF, Durbin-Watson, Breusch-Pagan and confidence and prediction inte…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Ordinary least squares by Householder QR with coefficient standard errors, t-tests and intervals, R-squared, F, VIF, Durbin-Watson, Breusch-Pagan and confidence and prediction intervals. Matches NIST StRD Norris and Longley. Price $0.05 USDC. POST /api/v1/statistics/linear-regression. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Fit a multiple linear regression
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • statistics_logistic-regressionBinary logistic regression by iteratively reweighted least squares with odds ratios and intervals, deviance, AIC, Hosmer-Lemeshow goodness of fit, a confusion matrix at a chosen th…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Binary logistic regression by iteratively reweighted least squares with odds ratios and intervals, deviance, AIC, Hosmer-Lemeshow goodness of fit, a confusion matrix at a chosen threshold and complete-separation detection. Price $0.05 USDC. POST /api/v1/statistics/logistic-regression. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Fit a binary logistic regression
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • statistics_nonparametric-testsMann-Whitney U, Wilcoxon signed-rank, Kruskal-Wallis, Friedman and sign tests with average-rank ties, exact p-values for samples up to 50 and tie-corrected normal approximations.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Mann-Whitney U, Wilcoxon signed-rank, Kruskal-Wallis, Friedman and sign tests with average-rank ties, exact p-values for samples up to 50 and tie-corrected normal approximations. Price $0.03 USDC. POST /api/v1/statistics/nonparametric-tests. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Run a nonparametric test
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • statistics_normality-testAnderson-Darling, Shapiro-Wilk (Royston AS R94) and Lilliefors tests of normality with optional normal probability plot coordinates.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Anderson-Darling, Shapiro-Wilk (Royston AS R94) and Lilliefors tests of normality with optional normal probability plot coordinates. Shapiro-Wilk and Anderson-Darling agree with SciPy and statsmodels. Price $0.03 USDC. POST /api/v1/statistics/normality-test. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Test data for normality
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • statistics_power-sample-sizePower or required sample size for a two-sample t-test (noncentral t), one-way ANOVA (noncentral F), two proportions (Cohen's h) and a correlation (Fisher z).Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Power or required sample size for a two-sample t-test (noncentral t), one-way ANOVA (noncentral F), two proportions (Cohen's h) and a correlation (Fisher z). Exactly one of n or power is solved. Price $0.02 USDC. POST /api/v1/statistics/power-sample-size. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Calculate statistical power or sample size
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • statistics_process-capabilityCp, Cpk, Pp, Ppk, Cpm and expected parts per million out of specification from individual values or subgroups, with R-bar, S-bar or pooled within-subgroup sigma, an optional Box-Co…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Cp, Cpk, Pp, Ppk, Cpm and expected parts per million out of specification from individual values or subgroups, with R-bar, S-bar or pooled within-subgroup sigma, an optional Box-Cox transform and a Bissell interval for Cpk. Price $0.04 USDC. POST /api/v1/statistics/process-capability. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Calculate process capability indices
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • statistics_t-testOne-sample, two-sample (Welch or pooled) and paired t-tests with the estimate, statistic, degrees of freedom, p-value, confidence interval and Cohen's d from caller-supplied number…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    One-sample, two-sample (Welch or pooled) and paired t-tests with the estimate, statistic, degrees of freedom, p-value, confidence interval and Cohen's d from caller-supplied numbers. Pure computation; no data is stored or fetched. Price $0.02 USDC. POST /api/v1/statistics/t-test. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Run a t-test with confidence interval
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • statistics_time-series-decomposeClassical moving-average additive or multiplicative decomposition into trend, seasonal indices and remainder, with Wang-Smith-Hyndman strength of seasonality and trend measures.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Classical moving-average additive or multiplicative decomposition into trend, seasonal indices and remainder, with Wang-Smith-Hyndman strength of seasonality and trend measures. STL is not provided. Price $0.03 USDC. POST /api/v1/statistics/time-series-decompose. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Decompose a seasonal time series
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • statistics_weibull-reliabilityMaximum-likelihood Weibull, lognormal or exponential life fits to right-censored failure data with Fisher-matrix confidence bounds, B-lives, reliability at chosen times and mean ti…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Maximum-likelihood Weibull, lognormal or exponential life fits to right-censored failure data with Fisher-matrix confidence bounds, B-lives, reliability at chosen times and mean time to failure. Price $0.05 USDC. POST /api/v1/statistics/weibull-reliability. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Fit a life distribution to censored data
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 1Show 1 read-only tool
  • statistics_doe-effects-analyzeEffects, coefficients and standardised effects for a two-level factorial, with Lenth's pseudo standard error and margin of error for unreplicated designs or a pure-error ANOVA when…Reads text others writeNo findings

    Why it is in this group

    • The name "statistics_doe-effects-analyze" says "analyze": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Effects, coefficients and standardised effects for a two-level factorial, with Lenth's pseudo standard error and margin of error for unreplicated designs or a pure-error ANOVA when runs are replicated, sorted as a Pareto of effects. Price $0.03 USDC. POST /api/v1/statistics/doe-effects-analyze. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Analyse two-level factorial effects
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:35 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
14
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 14 tools that change things (14 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://www.brainiac.software/mcp/statistics: tools/list returned 15 tools to an anonymous client, including statistics_t-test (write), statistics_anova (write), statistics_chi-square-test (write), statistics_nonparametric-tests (write), statistics_linear-regression (write) and 9 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "statistics_doe-design-generate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "statistics_doe-design-generate" says "generate": a word for a change.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools15 changed.~15 changedView diff

Install

Pinned to version 1.0.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http statistics https://www.brainiac.software/mcp/statistics
claude mcp add --transport http statistics https://www.brainiac.software/mcp/statistics

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__statistics__statistics_doe-effects-analyze"
    ],
    "ask": [
      "mcp__statistics__statistics_t-test",
      "mcp__statistics__statistics_anova",
      "mcp__statistics__statistics_chi-square-test",
      "mcp__statistics__statistics_nonparametric-tests",
      "mcp__statistics__statistics_linear-regression",
      "mcp__statistics__statistics_logistic-regression",
      "mcp__statistics__statistics_normality-test",
      "mcp__statistics__statistics_power-sample-size",
      "mcp__statistics__statistics_control-chart",
      "mcp__statistics__statistics_process-capability",
      "mcp__statistics__statistics_gage-rr",
      "mcp__statistics__statistics_doe-design-generate",
      "mcp__statistics__statistics_weibull-reliability",
      "mcp__statistics__statistics_time-series-decompose"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as statistics. Review it before you use it.

Capability tags behind 15 rules
  • mcp__statistics__statistics_t-test untrusted-input
  • mcp__statistics__statistics_anova untrusted-input
  • mcp__statistics__statistics_chi-square-test untrusted-input
  • mcp__statistics__statistics_nonparametric-tests untrusted-input
  • mcp__statistics__statistics_linear-regression untrusted-input
  • mcp__statistics__statistics_logistic-regression untrusted-input
  • mcp__statistics__statistics_normality-test untrusted-input
  • mcp__statistics__statistics_power-sample-size untrusted-input
  • mcp__statistics__statistics_control-chart untrusted-input
  • mcp__statistics__statistics_process-capability untrusted-input
  • mcp__statistics__statistics_gage-rr untrusted-input
  • mcp__statistics__statistics_doe-design-generate untrusted-input
  • mcp__statistics__statistics_doe-effects-analyze untrusted-input
  • mcp__statistics__statistics_weibull-reliability untrusted-input
  • mcp__statistics__statistics_time-series-decompose untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/software.brainiac/statistics/verify?hash=b4ec7d513d31eb4843ba9404e36e39b17b9ade9f61eb13ba28d57895f76dd0ce" | jq -e '.changed == false'

Pinned hash b4ec7d513d31, from Nov 20, 2026, 01:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/software.brainiac/statistics/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for software.brainiac/statistics
[![Anlyon Radar](https://radar.anlyon.com/badge/software.brainiac/statistics.svg)](https://radar.anlyon.com/servers/software.brainiac/statistics)

Source: MCP Registry. Synced Nov 20, 2026, 01:18 UTC.

BRAINIAC Statistics & Quality Engineering MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the BRAINIAC Statistics & Quality Engineering MCP server safe?

No scan can promise that. What its definitions show: 15 tools, 14 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the BRAINIAC Statistics & Quality Engineering MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the BRAINIAC Statistics & Quality Engineering MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the BRAINIAC Statistics & Quality Engineering MCP server have?

15 tools: 14 write, 1 read. statistics_t-test, statistics_anova, statistics_chi-square-test, statistics_nonparametric-tests, statistics_linear-regression, statistics_logistic-regression, statistics_normality-test, statistics_power-sample-size and 7 more.

Does the BRAINIAC Statistics & Quality Engineering MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the BRAINIAC Statistics & Quality Engineering MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the BRAINIAC Statistics & Quality Engineering MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.