idref_
1 MCP server offers this tool
What it usually takes
accept_threshold– in 1 of 1affiliation– in 1 of 1context– in 1 of 1embedding_model– in 1 of 1field– in 1 of 1margin_threshold– in 1 of 1max_candidates– in 1 of 1max_returned_candidates– in 1 of 1name– in 1 of 1works– in 1 of 1year– 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? |
|---|---|---|
Idref Resolver Mcp co.huggingface.geraldine/idref-resolver-mcp Align a person to an IdRef PPN from their name plus any disambiguating context. `best_ppn` is populated only when `status == "accepted"`. On any other status the alignment abstained: report the abstention, do not fall back to the top candidate's PPN. Raising a threshold makes the service stricter, i.e. more abstentions. Returns: {"source": "idref-resolver-api", "command": "align_person", "status": "accepted" | "ambiguous" | "low_confidence" | "not_found" | null, "best_ppn": str | null, "best_candidate": object | null, "candidates": [object], "candidates_scored": int, "similarity": object | null, "error": str | null} | accept_threshold,affiliation,context,embedding_model,field,margin_threshold,max_candidates,max_returned_candidates,name,works,year | Not stated |