timeseries-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TIMESERIES_MCP_DATA_ROOT | No | Root directory for loading CSV files. Paths are resolved against this directory and traversal outside is refused. | the server's working directory |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| load_csvA | Load one column of a CSV as a time series and register it under a series_id. |
| load_valuesA | Register a series from inline values (small data; prefer load_csv for files). |
| load_sampleA | Load a bundled synthetic sample (seeded, reproducible) — useful for demos and evals. |
| list_seriesA | List every series currently loaded, with basic stats. |
| describeC | Distributional summary: quartiles, spread, skewness, kurtosis, missing count. |
| get_windowA | Fetch raw observations in a time window (evenly thinned if over the limit). |
| resampleB | Resample onto a regular grid; registers and returns a NEW derived series. |
| rolling_statsA | Rolling-window statistics with an evenly spaced preview per stat. |
| data_qualityC | Audit sampling gaps, duplicate timestamps, missing values, and regularity. |
| detect_anomaliesA | Flag anomalous observations; returns scored anomalies, strongest first. |
| detect_changepointsB | Detect level shifts (mean changes) via CUSUM binary segmentation. |
| decomposeC | Split the series into trend/seasonal/residual and quantify each component's strength. |
| stationarityC | Run ADF and KPSS together and give a combined stationarity verdict. |
| autocorrelationC | ACF/PACF with significance bounds; suggests a seasonal period when one stands out. |
| trend_testC | Estimate trend three ways: OLS, robust Theil-Sen, and the Mann-Kendall test. |
| compare_seriesC | Correlate two series on shared timestamps and find the lag of strongest coupling. |
| forecast_baselineB | Baseline forecast with 95% intervals and an honest holdout backtest. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| analyze_series | Guided end-to-end analysis workflow for a loaded series. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| catalog_resource | Markdown table of every loaded series. |
TDQS
Scored across 17 tools
Each tool has a clearly distinct purpose: loading (three variants), listing, statistics, transformations, anomaly detection, decomposition, quality, comparison, and forecasting. There is no ambiguity; an agent can easily select the correct tool.
Most tools follow a verb_noun or descriptive verb pattern (e.g., load_csv, detect_anomalies, forecast_baseline). A few are single verbs (decompose, resample) or noun phrases (data_quality, stationarity), but the pattern is largely consistent and readable.
With 17 tools, the server covers a full range of time series operations—loading, inspection, transformation, analysis, anomaly detection, and forecasting—without being overwhelming. Each tool earns its place.
The toolset covers core lifecycle operations: loading, listing, description, resampling, rolling stats, quality checks, anomaly and changepoint detection, decomposition, stationarity, autocorrelation, trend tests, comparison, and baseline forecasting. Minor gaps (e.g., no differencing, no series deletion/export) are acceptable for analysis-focused servers.