Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Changed the definition of "checkRetraction"
⟨36 unchanged words⟩ it (clinical, regulatory, evidence-synthesis contexts).ForTomulti-papercheckbibliographyaauditsWHOLE reference list for retractions (clinicale.g.guidelines'check all these citations for retractions' at the end of a literature review, a guideline or a systematicreviewsreview),loopuseoneauditBibliographycallinsteadper—identifierone—calltherunstooltheintentionallyretractionrejectscheckbatchplusinputthetofabricationkeepcheckretraction-statusonresultsupunambiguoustoper25work.entries. Sourced from Crossref `updated-by` (which mirrors Retraction ⟨63 unchanged words⟩ per call — does NOT accept comma/newline batches; for a handful of papers loop one call per identifier, formultipleapapers.bibliography use auditBibliography. Returns: { doi, resolvedFrom?, reason?, result ⟨40 unchanged words⟩ resolved and reason explains why ('no_doi').No sibling tool overlaps this —resolveIdentifier returns metadata but not retractionstatus.status; auditBibliography includes this check for every entry of a bibliography. Read-only and idempotent — safe to retry. Works ⟨42 unchanged words⟩
Changed the definition of "auditBibliography"
⟨180 unchanged words⟩ total, matched, mismatch, ambiguous, not_found, not_checked, errored, retracted } }. `not_checked` counts entries declined before a verdict (no identifier, container-only identifier, too sparse) — report them as unverified, never as suspect. Reading the result: `index` is 1-BASED (entry ⟨203 unchanged words⟩
⟨211 unchanged words⟩ total, matched, mismatch, ambiguous, not_found, not_checked, errored, retracted }. `total` counts verifiable entries only, so it excludes `parseErrors` and anything past the cap. `not_found` = looked up and nothing exists; `not_checked` = declined before a verdict (no identifier in the reference, a container-only identifier, or too sparse to check) — tell the user those were NOT verified rather than treating them as suspect. `retracted` is a separate axis from the verdict ⟨51 unchanged words⟩
Changed the definition of "auditBibliography" and "verifyCitation"
⟨385 unchanged words⟩ ). Default false.","type":"boolean"},"semanticTitle":{"description":"Opt-in semantic title check applied per entry (any tier; see verifyCitation). Default false.","type":"boolean"}},"type":"object"}
⟨247 unchanged words⟩ Default false.","type":"boolean"},"semanticTitle":{"description":"Opt-in semantic title check (any tier). On a string-level matched verdict, a calibrated model judgment of whether the claimed and resolved titles describe the same work; catches one-word swaps in long titles that string similarity misses. A flagged title moves matched → ambiguous (review), never mismatch. Not byte-deterministic — _provenance.semantic_title carries the probability. Default false.","type":"boolean"},"title":{"description":"The title as it
Certificate changed, valid to 2026-12-14
Certificate changed, valid to 2026-12-13
Certificate recorded, valid to 2026-10-11
Authorization not required
First tool surface recorded: 7 tools (server version 0.8.11)
Showing the latest 8 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed