MCP For Claude Marketplace
Demand Forecast Calculator

Demand Forecast Calculator MCP Connector for Claude

A+

Generate 3-month demand projections using SMA, WMA, and Exponential Smoothing methods.

3 tools Official Updated Oct 1, 2026 Official Vinkius Partner
More Details Connect to Claude

This MCP server provides advanced forecasting capabilities to predict future demand based on historical data. It implements three distinct mathematical models: Simple Moving Average (analyze_sma), Weighted Moving Average (analyze_wma), and Exponential Smoothing (analyze_exponential_smoothing). For each method, the tools perform error backtesting to provide Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE), allowing you to identify the most accurate model for your specific dataset. Use these tools in Cursor, VS Code, Claude Desktop, or Windsurf to automate demand planning.

demand-planningsmawmaexponential-smoothingforecasting-engine

3 tools expose this connector's capabilities to your AI agent.

analyze_sma

Calculate demand forecast using Simple Moving Average (SMA)

analyze_exponential_smoothing

Calculate demand forecast using Exponential Smoothing

analyze_wma

Calculate demand forecast using Weighted Moving Average (WMA)

See how to talk to your AI agent using Demand Forecast Calculator.

Calculate a 3-month forecast using SMA with a window size of 3 for this demand: [10, 12, 15, 14, 18]

The `analyze_sma` tool has processed your data. The forecast for the next three months is [15.67, 15.67, 15.67] with a calculated MAPE of approximately 8.2%.

Use Exponential Smoothing to predict demand for [100, 110, 120] with alpha=0.5 and beta=0.3.

Using `analyze_exponential_smoothing`, the predicted demand for the next three periods is [130, 140, 150].

Analyze demand using WMA with weights [0.5, 0.3, 0.2] for data: [50, 60, 70]

The `analyze_wma` tool calculated the forecast as [76, 76, 76] based on your provided weights and historical sequence.

The server supports Simple Moving Average (`analyze_sma`), Weighted Moving Average (`analyze_wma`), and Exponential Smoothing (`analyze_exponential_smoothing`).

Related Connectors

Exponential Smoothing Engine

Exponential Smoothing Engine MCP

1 tools Official

Apply Simple Exponential Smoothing (Holt-Winters family) for local deterministic time-series forecasting.

A+ View details →
History Matching Quality

History Matching Quality MCP

4 tools Official

Quantifies the alignment between simulated reservoir production and observed historical data.

A+ View details →
Reservoir Prediction Uncertainty

Reservoir Prediction Uncertainty MCP

4 tools Official

Quantifies uncertainty in reservoir predictions using parameter ranges and correlations.

A+ View details →
Wine Vintage Rating Impact

Wine Vintage Rating Impact MCP

4 tools Official

Analyze how vintage quality affects wine price, demand, and inventory value.

A+ View details →