Classification Efficiency Model

Classification Efficiency Model MCP Connector for Claude

A+

Models classification efficiency for hydrocyclones and screens using partition curves and separation metrics.

4 tools Official Updated Oct 1, 2026 Official Vinkius Partner

This MCP server provides advanced mathematical modeling for mineral processing and particle separation. It allows AI agents to calculate partition curves, evaluate separation quality, and predict equipment performance for hydrocyclones and screens. Users can model the impact of the fish hook effect using simulate_fish_hook_impact or forecast stream distributions with predict_equipment_performance. The toolset includes analyze_partition_curve for generating probability distributions and calculate_separation_metrics for evaluating sharpness and efficiency.

hydrocycloneparticle-sizemineral-processingclassificationmodeling

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

analyze_partition_curve

Generates the probability distribution for particle recovery across a range of sizes

calculate_separation_metrics

Evaluates the quality of the classification based on feed and partition data

predict_equipment_performance

Forecasts the resulting size distribution of the underflow and overflow streams

simulate_fish_hook_impact

Predicts how the fish hook effect will alter the predicted recovery of fine particles

See how to talk to your AI agent using Classification Efficiency Model.

Generate a partition curve for a cut size of 50 microns, a sharpness index of 1.5, and a bypass fraction of 0.1.

The generated partition curve shows a probability distribution centered around the 50 micron cut size, adjusted for the 0.1 bypass fraction.

What happens to the recovery if there is a fish hook effect at 20 microns with a magnitude of 0.05?

The adjusted curve shows an increased recovery of fine particles near the 20 micron size due to the specified deviation.

Calculate the separation metrics for a feed distribution and a specific partition curve.

The calculated metrics show a sharpness of 1.4, a bypass of 0.08, and an overall efficiency of 85%.

You can use `calculate_separation_metrics` after generating a partition curve with `analyze_partition_curve` to determine sharpness and efficiency.

Related Connectors