pdac_subtype_agent_prod__run_findings – 1 MCP server offers this tool
What it usually takes
columns– in 1 of 1dataset_id– in 1 of 1sample_selection– in 1 of 1sets– in 1 of 1stratify_by– in 1 of 1
No server marks it as only reading: treat it as able to change data.
From each publisher's own tool list. We never call a tool.
Servers
| Server | Inputs | Read-only? |
|---|---|---|
PDAC Subtype Agent co.huggingface.anne-voigt/pdac-subtype-agent-prod Machine door for the ADR-0028 ranking: score, then rank against the cohort's obs. Why this exists as its OWN endpoint rather than a `findings` block bolted onto ``score_signatures``. ``agents.yaml`` describes what the orchestrator may CALL, and the file records its own hard lesson twice: a capability declared but not delivered is worse than one not declared, because the tool-extraction call picks it confidently. The findings panel shipped UI-only, so until this endpoint existed the orchestrator could not obtain a ranking at all — and routing "which pathway differs most?" to ``score_signatures`` would have handed its summarizer 58 sets x N samples of raw scores and left it to invent the ordering. That is exactly the LLM free-association ADR-0027 §4 and ADR-0028 §5 forbid: the whole point is that the narrative restates a computed row. Extending ``score_signatures`` instead was rejected — it would change a payload the orchestrator already parses, and make every scoring call pay a dataset | columns,dataset_id,sample_selection,sets,stratify_by | Not stated |