Sports Context Protocol

A self-learning context layer for AI agents booking golf tee times. Exposes 11 MCP resources (tee sheets, pricing policy, booking rules, pace data, event blocks) and 9 tools including booking and pricing safety checks, soft holds, and a decision ledger. The learning loop is the real piece: agents log decisions with fingerprints, submit outcome feedback (operator overrides, pace issues, pricing rejections), and SCP adjusts recommendations for similar future decisions without retraining models. Built on a synthetic demo course with member protections, league blocks, and inventory state. Useful if you're building golf booking agents that need to respect course operating constraints and learn from corrections instead of just executing API calls blindly.