Skip to main content
Glama
omnioperand-mcp

omnioperand-mcp

omni_cohort_retention_churn

Calculate 30-day, 90-day, and annual cohort retention and churn rates from acquisition cohort sizes to replace manual arithmetic with deterministic, precise results.

Instructions

Customer Cohort Retention & Churn Rate Calculator. Analyze multi-month customer retention curves across acquisition cohorts to calculate 30-day, 90-day, and 365-day retention and churn rates. Discipline: ECOMMERCE. Governing mathematical model / formula: Retention Rate M_t = (Active Customers at Month t / Initial Cohort Size) × 100 | Churn Rate = 100% - Retention Rate.

USAGE GUIDELINES:

  • WHEN TO USE: Invoke for deterministic calculation of month_1_retention_pct (Month 1 (30-Day) Retention), month_3_retention_pct (Month 3 (90-Day) Retention), annual_retention_pct (Month 12 (Annual) Retention), annual_cohort_churn_pct (Cumulative 1-Year Cohort Churn) using initial_cohort_customers (Initial Cohort Acquired Customers (M0) in users), month_1_retained (Month 1 (30-Day) Active Customers in users), month_3_retained (Month 3 (90-Day) Active Customers in users), month_12_retained (Month 12 (1-Year) Active Customers in users). Guarantees exact machine floating-point precision, eliminating LLM arithmetic mistakes and formula hallucinations.

  • WHEN NOT TO USE: Do not use for qualitative evaluations or unquantified reasoning. All input parameters must be valid numerical values.

DISAMBIGUATION & BOUNDARIES:

  • Use this dedicated specialist tool for 'Customer Cohort Retention & Churn Rate Calculator' rather than generic dispatchers like omni_universal_query.

  • For multi-calculation chained jobs, use 'omni_batch_calculate'.

  • To inspect schema fields, see 'omni_describe_solver'.

BEHAVIOR & SAFETY:

  • Pure deterministic computation with machine floating-point precision.

  • Read-only, idempotent, and stateless. Zero side effects or persistent state mutations.

  • Input validation: All arguments are validated against physical and domain bounds. Out-of-bounds inputs return a safe diagnostic error status without throwing runtime exceptions.

RETURNS:

  • Structured JSON object containing:

    • status (string): "success" on valid execution or "error" if validation fails

    • calculator (string): "cohort-retention-churn"

    • category (string): "ecommerce"

    • name (string): "Customer Cohort Retention & Churn Rate Calculator"

    • formula (string): Governing mathematical formula string

    • inputs (object): Echoed input parameter dictionary with applied defaults

    • metrics (object): Dictionary of computed outputs:

      • metrics.month_1_retention_pct (Month 1 (30-Day) Retention): Formatted display string (e.g. '45.0%')

      • metrics.month_3_retention_pct (Month 3 (90-Day) Retention): Formatted display string (e.g. '30.0%')

      • metrics.annual_retention_pct (Month 12 (Annual) Retention): Formatted display string (e.g. '18.0%')

      • metrics.annual_cohort_churn_pct (Cumulative 1-Year Cohort Churn): Formatted display string (e.g. '82.0%')

    • execution_time_ms (number): Latency in milliseconds.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "omni_cohort_retention_churn"
  }
}

Input Schema

NameRequiredDescriptionDefault
month_1_retainedNoMonth 1 (30-Day) Active Customers (users). Customers who purchased or renewed in month 1. Default: 1125. Min: 0. Max: 500000.
month_3_retainedNoMonth 3 (90-Day) Active Customers (users). Customers still active at 90 days. Default: 750. Min: 0. Max: 500000.
month_12_retainedNoMonth 12 (1-Year) Active Customers (users). Customers still active at 1 full year. Default: 450. Min: 0. Max: 500000.
initial_cohort_customersNoInitial Cohort Acquired Customers (M0) (users). New customers acquired in base month. Default: 2500. Min: 50. Max: 500000.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.2

TDQS

Score is being calculated.

Deploy Server

Other Tools