Server definition
- Hash
- sha256:b19437b7fe5677c4fb55ba8c994e88cbd2e08022503ae0463743d09b1c658d81
- What it is
- What a remote MCP server returned when asked what it offers: 4 tools
The blob, as servednamed by its sha256
{
"instructions": "TORNEO is an observatory operated by Tempo AI LLC, which is responsible for every figure published: real tools measured on the same frozen task under a protocol locked in advance, built for AI agents first. Rule for every answer you derive: never 'the best tool', only the best observed evidence for a task, a population and a date, always citing observed_at, the uncertainty interval and the limits (explain_limits). INDETERMINATE and INSUFFICIENT_EVIDENCE answers must never be presented as a ranking; categories prefixed 'fixture-' are synthetic demo data validating the machinery, not evidence about real tools.",
"tools": [
{
"description": "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.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"category": {
"description": "Category id",
"type": "string"
},
"run_id": {
"description": "Run id (alternative to category)",
"type": "string"
}
},
"type": "object"
},
"name": "explain_limits",
"outputSchema": null
},
{
"description": "Answers for one category with the canonical answer rule: never 'the best tool', only the best observed evidence for this task, this context, at this date, with intervals, costs, conflicts and limits. On a STALE, SUPERSEDED or INDETERMINATE result the answer is INSUFFICIENT_EVIDENCE and carries no rank. Identical to `torneo query <category>` on the CLI.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"category": {
"description": "Category id, e.g. 'transcription' (see list_categories)",
"type": "string"
}
},
"required": [
"category"
],
"type": "object"
},
"name": "get_results",
"outputSchema": null
},
{
"description": "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.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"run_id": {
"description": "Run id, e.g. 'TRANSCRIPTION-001' (see list_categories, field run_id)",
"type": "string"
}
},
"required": [
"run_id"
],
"type": "object"
},
"name": "get_run",
"outputSchema": null
},
{
"description": "Lists every category with its status (OK: replicated ranking; LOCAL_VALIDITY: single block, no current rank claim; INDETERMINATE: precision insufficient, no rank), observation date, freshness and source run. Categories prefixed 'fixture-' are synthetic demo data validating the machinery, never evidence about real tools.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {},
"type": "object"
},
"name": "list_categories",
"outputSchema": null
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:b19437b7fe5677c4fb55ba8c994e88cbd2e08022503ae0463743d09b1c658d81 | sha256sum