ART MCP Server
Related Servers
Alternatives to ART MCP Server
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables time-series analysis and forecasting through a structured tool catalogue, including data loading, quality repair, diagnostics, and forecasting with ARIMA, exponential smoothing, Chronos-2, Toto 2.0, and AutoML.1MIT
- FlicenseNot gradedqualityBmaintenanceEnables LLM agents to run iterative volatility analytics, from pre-flight statistical gates through GARCH-family model fitting, VaR/ES risk metrics, and Basel backtesting, with a feedback loop guiding each step.-
- AlicenseBqualityDmaintenanceEnable any AI agent to forecast time-series data (e.g., sales, traffic) using Google's TimesFM or a zero-dependency statistical baseline.3Apache 2.0
- AlicenseAqualityCmaintenanceDeterministic time-series statistics for AI agents. This MCP server gives any LLM agent unit-tested statistical tools — anomaly detection, changepoint detection, seasonal decomposition, stationarity/trend tests, data-quality audits, baseline forecasts — with schema-validated structured output and no arbitrary code execution.17MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server powered by Meta's Prophet that enables LLMs to perform time-series forecasting, trend analysis, and predictive modeling on historical data. It provides LLM-friendly statistical summaries, automated business-rule validation, and ready-to-render Chart.js visualizations.MIT
- AlicenseNot gradedqualityCmaintenanceProvides a virtual statistician for AI agents, offering real statistical methods such as design of experiments, hypothesis testing, regression, and process control. It includes an advisor tool to recommend appropriate analyses and generates plain-language interpretations of results.MIT
TDQS
Scored across 35 tools
Many tools share overlapping purposes (e.g., confirm_and_estimate, estimate_and_diagnose, build_model, guided_identification all involve estimation/diagnosis; preliminary_outlier_scan and intervention_analysis both address outliers). Detailed descriptions help distinguish them, but an agent could easily select the wrong tool without careful reading.
Names follow no consistent pattern: some are verb_noun (create_inp, load_data, generate_forecast), some are noun_phrase (series_info, model_equation_display), and others are compound descriptions (overparameterization_analysis, test_seasonal_simplification). The mixed styles and lack of a uniform verb/noun convention make the set feel chaotic.
35 tools is high for a time-series modeling server, even a complex one. Many are narrow diagnostic/support tools that could be consolidated (e.g., multiple analysis tools, several test functions). The count exceeds the 25+ threshold for 'too many' and adds cognitive overhead.
The tool surface covers the full modeling lifecycle: data intake, transformation analysis, identification, estimation, diagnosis, formal testing, intervention handling, forecasting, reporting, and versioning. Minor gaps exist (e.g., no explicit data export, no tool for removing interventions), but the workflow is essentially complete.