For statistical analysis, the most directly relevant options are Anthropic's statistical-analysis action covering descriptive stats, trend analysis, outlier detection and hypothesis testing 111, K-Dense's guided statistical-analysis action covering test selection, assumption checking, effect sizes and power analysis 212, and MCP Analytics, which runs statistical analyses on uploaded data and returns a shareable report with the method named 414. Statsmodels, R and Stan are established
- 1
- 2
K-Densek-dense.aiverified and signed
Its statistical-analysis action gives guided analysis of research data, including test selection, assumption checking, effect sizes, power analysis and Bayesian alternatives 12.
for agents: statistical-analysis · statistical-power · statsmodels
- 3
MCP Analyticsmcpanalytics.aiverified and signed
It runs statistical analysis on uploaded data through its run analysis action and returns an interactive report URL with statistics and the method name 14.
official:MCP server · MCP Analytics
for agents: run analysis · create analysis · modify analysis
- 4
Statsmodelsstatsmodels.orgverified and signed
A Python library for fitting and diagnosing statistical models such as OLS, GLM, mixed models and ARIMA; this source page does not describe its actions.
for agents: statistical · statistics · anova
- 5
Stanmc-stan.orgwebsite read, tools not yet checked
A probabilistic programming language for Bayesian statistical modeling, with interfaces for Python, Julia and R 3.
Sources
- 1Home \ Anthropicanthropic.com · read 2026-10-29
- 2K-Dense | AI Agents for Real Researchk-dense.ai · read 2026-10-30
- 3Stanmc-stan.org · read 2026-10-30
- 4MCP Analytics: Statistical Analysis You Can Defendmcpanalytics.ai · read 2026-10-29
- 5Statsmodelsstatsmodels.org · read just now
- 11statistical-analysis: declares "statistical-analysis" (the record we read and signed)unfragile.ai · read 2026-10-24
- 12statistical-analysis: declares "statistical-analysis" (the record we read and signed)unfragile.ai · read 2026-10-24
- 14MCP Analytics: declares "run analysis" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
statistical-analysis · statistical-analysis verified and signed
Apply statistical methods including descriptive stats, trend analysis, outlier detection, and hypothesis testing. Use when analyzing distributions, testing for significance, detecting anomalies, computing correlations, or interpreting statistical results.
statistical-analysis · statistical-analysis verified and signed
Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting. Use whenever a user wants to compare groups, test a hypothesis, analyze experimental or survey data, check statistical assumptions, c
· Mc-stan website read, tools not yet checked
Stan combines powerful statistical modeling capabilities with user-friendly interfaces, an active community, and a commitment to open-source development.
run analysis · MCP Analytics verified and signed
Run an analysis on your data. Returns a shareable interactive report URL with statistics you can cite, re-run and share, and the method named.
statistical · statsmodels verified and signed
testing · hypothesis verified and signed
content-experimentation-best-practices · content-experimentation-best-practices verified and signed
Content experimentation and A/B testing guidance covering experiment design, hypotheses, metrics, sample size, statistical foundations, CMS-managed variants, and common analysis pitfalls. Use this skill when planning experiments, setting up variants, choosing success metrics, interpreting statistica
OLAP · duckdb verified and signed
· R-project website read, tools not yet checked
· NextStat website read, tools not yet checked
Rust-powered statistical inference engine with Python API. Survival analysis, econometrics, machine learning, and particle physics — frequentist and Bayesian methods with SIMD, CUDA, and Metal GPU acceleration. AGPL-3.0.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.