auditBibliography
Run the verifyCitation check plus a retraction lookup across a whole bibliography in one call. Accepts raw BibTeX, RIS, or CSL-JSON text, or a pre-parsed claims[] array; returns a per-entry verdict table and a corpus summary. Capped at 25 entries per call.
How to use it
auditBibliography is exposed by the Scholar Sidekick MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the auditBibliography tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Scholar Sidekick MCP
claude mcp add scholar-sidekick -- npx -y scholar-sidekick-mcp@latestOther tools in Scholar Sidekick MCP (6)
Check whether a single work is openly accessible and where to find the best legal version. Sourced from Unpaywall. Returns OA status (gold/green/hybrid/bronze/closed), best landing/PDF URL, license, and version. Resolves DOI/PMID/PMCID/arXiv/ISBN/ADS inputs to a DOI before lookup. One identifier per
Check whether a single work has been retracted, corrected, or had an expression of concern raised. Sourced from Crossref updated-by (Retraction Watch). Resolves DOI/PMID/PMCID/arXiv/ADS inputs to a DOI before lookup. One identifier per call.
Export one or many identifiers to BibTeX, RIS, CSL JSON, EndNote (XML/Refer), RefWorks, MEDLINE, Zotero RDF, CSV, or plain text — ready to write to disk or hand to a reference manager.
Format one or many identifiers into Vancouver, AMA, APA, IEEE, CSE, or any of 10,000+ CSL styles. Output as text, HTML, or JSON. Returns formatted citations plus a provenance metadata block.
Resolve DOIs, PMIDs, PMCIDs, ISBNs, arXiv IDs, ISSNs, ADS bibcodes, and WHO IRIS URLs to structured bibliographic metadata (CSL JSON). Accepts a single identifier or a comma/newline-separated batch.
Verify a claimed citation against the resolved record at its identifier. Detects the Topaz et al. (Lancet 2026) fabrication pattern — real DOI + invented title — that resolveIdentifier alone cannot catch. Returns one of four verdicts (matched / mismatch / ambiguous / notfound) plus per-field similar