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.
- tools
- 9
- transport
- STDIO
- last updated
- May 22, 2026
Tools
9 toolsPublic tool metadata for what this MCP can expose to an agent.
get_course_contextFull operating context — read this before acting.
Full operating context — read this before acting.
No parameter schema in public metadata yet.
get_available_inventoryAvailable tee times near a preferred time.
Available tee times near a preferred time.
No parameter schema in public metadata yet.
check_booking_actionIs a booking allowed, blocked, risky? Writes a decision.
Is a booking allowed, blocked, risky? Writes a decision.
No parameter schema in public metadata yet.
check_pricing_actionIs a quoted/discounted price allowed? Writes a decision.
Is a quoted/discounted price allowed? Writes a decision.
No parameter schema in public metadata yet.
create_soft_holdTemporary hold on a tee time before confirmation.
Temporary hold on a tee time before confirmation.
No parameter schema in public metadata yet.
write_decision_eventLog a decision directly.
Log a decision directly.
No parameter schema in public metadata yet.
submit_outcome_feedbackThe learning tool. Feed an outcome back to SCP.
The learning tool. Feed an outcome back to SCP.
No parameter schema in public metadata yet.
get_learning_insightsWhat SCP has learned.
What SCP has learned.
No parameter schema in public metadata yet.
explain_actionExplain a result for golfer / operator / developer.
Explain a result for golfer / operator / developer.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
SCP Golf — Profile 001 of the Sports Context Protocol
The context, safety, and memory layer for sports agents. Golf first.
Before a sports agent acts, it checks SCP. Then SCP learns from what happened.
SCP — Sports Context Protocol — is an open context layer for AI agents operating in sports. Every sport venue has the same five things underneath: inventory, rules, actions, consequences, and memory. SCP is the standard way an agent reads those before it acts, and learns from the outcome after.
SCP Golf is Profile 001 — the first working profile. Golf is the cleanest wedge because an agent cannot safely book, price, move, or recommend anything at a course without understanding tee-sheet state, protected inventory, pricing policy, pace risk, events, and operator memory. Golf makes the problem impossible to ignore.
This repository is SCP Golf Alpha: a synthetic demo course, a local MCP server, booking and pricing safety checks, soft holds, a decision ledger, and a self-learning memory. No real course data, no integrations, no database.
Details
- Repository
- github.com/dswane/sports-context-protocol
- Website
- github.com/Dswane/Sports-Context-Protocol#readme
- Package
sports-context-protocol- Transport
- STDIO
- Registry
- MCP registry, active