forecast-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| list_skusA | List every SKU/series id available in the loaded dataset. |
| classify_demand_patternB | Classify a SKU's demand pattern (Syntetos-Boylan: smooth / erratic / intermittent / lumpy / cold_start) and the model tier it routes to. |
| forecast_seriesA | Forecast future demand for a SKU. Automatically classifies the series first and routes to the matching model: mean fallback for cold-start SKUs, TSB for intermittent demand, AutoETS for regular continuous demand. |
| evaluate_forecastA | Backtest a SKU's forecast: hold out the last |
| recommend_replenishmentA | Recommend a reorder quantity for a SKU: forecasts demand, then applies a reorder-point / safety-stock formula against current on-hand stock. |
| explain_forecastA | Return a plain-language explanation of why a SKU was routed to the model tier it was, for surfacing to a non-technical user. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool targets a distinct action: listing, classifying, forecasting, evaluating, recommending, and explaining. There is no overlap between classification and explanation, and forecast_series complements rather than duplicates classify_demand_pattern.
All tool names follow a consistent verb_noun pattern in snake_case (list_skus, classify_demand_pattern, forecast_series, evaluate_forecast, recommend_replenishment, explain_forecast). No mixed conventions or vague verbs.
Six tools is well within the 3-15 range and each covers an essential function for the forecasting domain. The set feels neither sparse nor bloated.
The set covers the core workflow: listing SKUs, classifying demand, forecasting, backtesting, replenishment, and explanation. A minor gap is lack of a dedicated tool to inspect raw historical demand data, but agents can work around it via the other tools.