MCP 서버

torneo

io.github.devlollc/torneo
데이터 및 분석 공개 · 연결 가능 MCP 2025-11-25

이 MCP로 할 수 있는 일

Provides evidence-based benchmark results, run bundles, category status, provenance, intervals, and limitations for observed tool evaluations.

explain_limits
Explain the limits of a result
Returns what a category's (or run's) result can and cannot tell you: status and its meaning, fixture flag, freshness, expiry, explicit limits, conflicts, funding, published errata (each chained to the served result hash), the legal preflight verdict per tool including tools not run, and the answer rule every consumer must follow.
입력 스키마
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'run_id': {'type': 'string', 'description': 'Run id (alternative to category)'}, 'category': {'type': 'string', 'description': 'Category id'}}}
get_results
Query the evidence for a category
Answers for one category with the canonical answer rule: never 'the best tool', only the best observed evidence for this task, this context, at this date, with intervals, costs, conflicts and limits. On a STALE, SUPERSEDED or INDETERMINATE result the answer is INSUFFICIENT_EVIDENCE and carries no rank. Identical to `torneo query <category>` on the CLI.
입력 스키마
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['category'], 'properties': {'category': {'type': 'string', 'description': "Category id, e.g. 'transcription' (see list_categories)"}}}
get_run
Get a run bundle
Returns the canonical result bundle of one run (schema result.v1): protocol lock hash, provenance, reproduce command, per-participant outcomes with intervals. A PRE-REGISTERED run, whose protocol is frozen and timestamped but which has not been executed, returns state PRE_REGISTERED with measured false, its lock and its frozen files, and no result: nothing has been measured yet.
입력 스키마
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['run_id'], 'properties': {'run_id': {'type': 'string', 'description': "Run id, e.g. 'TRANSCRIPTION-001' (see list_categories, field run_id)"}}}
list_categories
List categories
Lists every category with its status (OK: replicated ranking; LOCAL_VALIDITY: single block, no current rank claim; INDETERMINATE: precision insufficient, no rank), observation date, freshness and source run. Categories prefixed 'fixture-' are synthetic demo data validating the machinery, never evidence about real tools.
입력 스키마
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {}}
추가됨
explain_limits
2026년 9월 17일 12:41 PM
추가됨
get_run
2026년 9월 17일 12:41 PM
추가됨
get_results
2026년 9월 17일 12:41 PM
추가됨
list_categories
2026년 9월 17일 12:41 PM