io.github.Dswane/sports-context-protocol
Sports Context Protocol
Self-learning operational context layer for AI sports agents. Profile 001: golf.
alive probed 2026-10-14
9tools
2.3ktokens in Claude Opus 5.5
2.4ktokens in Claude Code
1.1 %of a 200k context window
1.2ko200k_base estimate
266 msto initialize
11 msto list tools
- Run it
- npx -y sports-context-protocol@0.1.2 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- sports-context-protocol 0.1.0
- Capabilities
- prompts, resources, tools
- Instructions
- none
- Claude count
- Claude Opus 5.5, measured 2026-10-14. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/Dswane/Sports-Context-Protocol
- Website
- https://github.com/Dswane/Sports-Context-Protocol#readme
- Registry
- active, updated 2026-05-22 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| write_decision_event | 207 | 17 % |
| check_booking_action | 150 | 12 % |
| check_pricing_action | 148 | 12 % |
| submit_outcome_feedback | 148 | 12 % |
| create_soft_hold | 136 | 11 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.Dswane/sports-context-protocol)
An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.