SCP Golf MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_course_contextA | Returns the full operating context for the course: tee-sheet summary, inventory, booking and pricing policies, events, weather, pace risks, recent decisions, and learning insights. An agent should call this before acting. |
| get_available_inventoryB | Finds available tee times near a preferred time. Never returns protected, booked, or blocked inventory as bookable. |
| check_booking_actionC | Checks whether a booking is allowed, blocked, risky, or warns based on policy and learned memory. Writes a decision event to the ledger. |
| check_pricing_actionB | Checks whether a quoted or discounted price is allowed, given the absolute floor, time-window rate, discount limits, approval rules, and learned pricing patterns. Writes a decision event. |
| create_soft_holdC | Creates a temporary hold on a tee time before confirmation. Marks the slot as soft_hold on the tee sheet. |
| write_decision_eventB | Logs a decision event to the ledger. Most decision tools write their own events; this tool is for agents that want to log an action directly. |
| submit_outcome_feedbackC | The learning tool. Attaches an outcome to a past decision and updates SCP's learning memory so future similar decisions improve. |
| get_learning_insightsC | Returns what SCP has learned: lessons, operator preferences, pricing and pace patterns, and similar past decisions. Optionally filtered to a decision fingerprint key. |
| explain_actionB | Explains a decision result for a chosen audience: golfer (simple, no internal language), operator (operational detail), or developer (structured detail). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| analyze_booking_request | Analyze a golfer booking request end to end using SCP Golf. |
| operator_morning_briefing | Generate a morning operations briefing for staff. |
| explain_blocked_booking | Explain why a booking is blocked or not recommended, for a given audience. |
| review_learning_memory | Summarize what SCP Golf has learned. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| course | The demo course profile. |
| context | The full course operating context — read this before acting. |
| tee-sheet | The full tee sheet for the demo date. |
| booking-policy | Booking policy: agent rules, approval rules, soft holds. |
| pricing-policy | Pricing policy: rates, floor, discount and approval rules. |
| events | Internal event blocks for the demo date. |
| weather | Weather context for the demo date. |
| pace | Pace-of-play context and risk windows. |
| decision-ledger | The decision ledger — every logged decision event. |
| learning-memory | SCP's learning memory — lessons and patterns. |
| soft-holds | Active and historical soft holds. |
TDQS
Scored across 9 tools
Each tool has a clearly distinct purpose: context retrieval, inventory lookup, policy checks, hold creation, decision logging, feedback, insights, and explanation. No overlap in functionality.
All tool names follow a consistent verb_noun pattern in snake_case, using imperative verbs like get_, check_, create_, write_, submit_, explain_. No mixing of conventions.
9 tools is perfectly scoped for a golf course management domain, covering context, inventory, policies, actions, logging, learning, and explanation without excess.
Covers core workflows: context, inventory, booking/pricing checks, holds, decision logging, and learning. Minor gap: no explicit release or confirm tool, but temporary holds auto-expire as per description.