About Timeseries MCP
Timeseries MCP is an MCP server published by Lkhanaajav in the Science category: mCP server supporting multiple time series analysis models.
Recent commit activity is the strongest signal that reported issues will get attention.
Install
git clone https://github.com/Lkhanaajav/timeseries-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (9)
autocorrelationACF/PACF, significance bounds, seasonal-period suggestion
Parameters not published.
compare_seriesPearson/Spearman on shared timestamps + best lead/lag scan
Parameters not published.
data_qualityGaps, duplicate timestamps, missing values, sampling regularity
Parameters not published.
decomposeSTL / classical split + Hyndman trend/seasonal strength (0–1)
Parameters not published.
detect_anomalies`zscore`, `mad` (robust), `iqr`, `stl_residual` (seasonal-context)
Parameters not published.
detect_changepointsLevel shifts via CUSUM binary segmentation, MAD-robust noise scale
Parameters not published.
forecast_baselinenaive / seasonal-naive / drift / SES, 95% intervals, **holdout backtest included**
Parameters not published.
stationarityADF + KPSS read together, combined verdict + differencing hint
Parameters not published.
trend_testOLS + robust Theil-Sen + Mann-Kendall (tie-corrected)
Parameters not published.
Ask AI
Ask AI about Timeseries MCP
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.