@modelcontextprotocol/server-cohort-heatmap

Generates interactive retention heatmaps by organizing users into cohorts (grouped by signup/activation date) and tracking their engagement metrics across time periods. The server implements a cohort analysis engine that accepts raw event data, buckets users into temporal cohorts, calculates retention rates per cohort-period intersection, and renders the data as a structured heatmap matrix suitable for visualization. This enables product teams to identify retention patterns and cohort-specific engagement trends without manual data aggregation.

Partitions users into cohorts based on temporal boundaries (e.g., signup week, activation month) and aggregates engagement metrics within each cohort-period cell. The implementation accepts raw event streams, applies configurable time-window functions to assign users to cohorts, and computes retention/engagement statistics per cohort without requiring pre-computed aggregations. This enables flexible cohort definitions and supports ad-hoc analysis without data warehouse dependencies.

Computes retention rates, churn rates, and engagement metrics across cohort-period intersections using configurable metric definitions. The server accepts event data and metric specifications (e.g., 'user is retained if they had any event in the period'), calculates the metric for each cohort-period cell, and returns a normalized heatmap suitable for visualization. Supports multiple retention definitions (e.g., DAU-based, transaction-based, feature-specific) without requiring separate data pipelines.

Exposes cohort analysis capabilities as MCP server tools, enabling LLM clients and AI agents to invoke cohort generation, retention calculation, and heatmap rendering through the Model Context Protocol. The server implements tool schemas that define input parameters (event data, cohort config, metric definitions) and output formats, allowing Claude and other MCP-compatible clients to autonomously call these tools within agentic workflows. This enables conversational data analysis where users describe retention questions in natural language and the agent executes the appropriate analysis.

Transforms aggregated retention metrics into a structured heatmap matrix (cohort × time_period grid) and serializes it to JSON for downstream visualization or reporting. The implementation organizes retention data into a normalized tabular format with cohort identifiers as rows, time periods as columns, and retention percentages as cell values, optionally including metadata (cohort size, absolute retention counts). This enables consistent data exchange between the analysis engine and visualization tools.