Epoch is a time estimation MCP server that gives AI agents grounded, data-driven scheduling capabilities across 25 tools, replacing guesswork with established estimation methods.

Time & Calendar Operations

• Get current time in any IANA timezone, convert timestamps, and parse human-readable durations (e.g., 2h30m, 1w3d)

• Add or count business days with public holiday support for US, UK, FR, DE, and JP

Estimation Methods

• PERT three-point estimation with confidence intervals and urgency scoring

• COCOMO II LLM-adapted software sizing returning nominal and AI-adjusted person-months

• Sprint velocity forecasting from historical sprint data

• Critical Path Method (CPM) with slack per task and merge-bias adjustment

• Monte Carlo simulation for probabilistic schedule risk (P10/P50/P80/P95)

Analytics & Reference Class Forecasting

• Data-driven estimates from 126,223+ real task data points with planning fallacy correction

• Classify free-text task descriptions and auto-delegate to reference class forecasting

• Compute team-specific correction factors from historical estimated vs. actual data

• Map LLM token budgets to wall-clock time for 12 model families

Cost & Risk Analysis

• Estimate token costs and wall-clock time for LLM API calls by model

• Side-by-side model comparison by cost, speed, and quality

• Schedule risk scoring with confidence intervals (P50/P80/P95)

• Validate COCOMO estimates against 195–240 real historical projects (NASA93, COCOMO81, etc.)

Feedback & Self-Improvement

• Record actual hours against previous estimates to calibrate future accuracy

• Batch-record up to 500 actuals at once

• Track accuracy trends over time (sliding-window MAPE by tool/task type)

• Monitor feedback loop health and self-improvement readiness

• All self-improvement data stored locally and privately, with optional opt-in for anonymized community sharing