r-stats-mcp
Related Servers
Alternatives to r-stats-mcp
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityDmaintenanceMCP server that lets AI agents discover and call R and Python statistical functions without writing code.-
- AlicenseNot gradedqualityCmaintenanceA statistical analysis MCP server offering 30 tools for descriptive statistics, hypothesis tests, regression, and time series, all returning Markdown reports with automatic interpretations to enable AI agents to perform comprehensive data analysis.MIT
- AlicenseAqualityAmaintenanceAn MCP server that lets Large Language Models interact with Stata software to perform regression analysis and other statistical operations.43,652 PyPI261AGPL 3.0
- AlicenseNot gradedqualityDmaintenanceMCP server that enables verified code execution with LLM reasoning using Recursive Language Models (RLM). It supports tasks like code generation, data analysis, and complex task decomposition.2MIT
- AlicenseAqualityDmaintenanceAn MCP server that enables AI assistants to call statistician's decision logic for recommending statistical tests, checking assumptions, interpreting results, and planning sample sizes.6MIT
- FlicenseAqualityDmaintenanceAn MCP server for dataset exploration and analysis, enabling LLM clients to perform summary, correlation, distribution, missing value analysis, data cleaning, and statistical tests directly on CSV files.3-
TDQS
Scored across 33 tools
Most tools are clearly separated by domain (data_, test_, model_, survey_), and the survey_* tools are well distinguished by their design-corrected standard errors. However, check_assumptions and model_diagnostics overlap heavily when given a fitted model: both report residual normality, Breusch-Pagan, Durbin-Watson, VIF and the diagnostic plots, which could lead an agent to pick the wrong tool.
The set uses snake_case throughout and useful prefixes (data_, test_, model_, survey_) give a predictable pattern. It is not perfect: r_session_info vs session_clear splits the r_/session_ prefix, and a few commands are bare nouns (describe, correlation, sem, plot) rather than verb_noun forms.
33 tools is well above the 25+ threshold and will burden an agent with a very large action space. Each tool is individually defensible for a broad statistics server, but the set could be consolidated—for example, survey_mean, survey_regression and survey_correlation share a lot of design specification boilerplate.
The surface is remarkably complete: data ingestion/inspection/transform/export, descriptives, common tests, regression with diagnostics/comparison/prediction, survey methods, psychometrics, SEM, mediation/moderation, survival and time series are all covered. The r_run escape hatch also prevents dead ends for any analysis the structured tools do not anticipate.