Server definition
- Hash
- sha256:0f1a8c057b61b2f98a35a6464a38f84de66dbed823c62b56ed728cde12ec1bde
- What it is
- What a remote MCP server returned when asked what it offers: 7 tools
The blob, as servednamed by its sha256
{
"instructions": "Scholar Sidekick is a citation-integrity server: it catches fabricated citations, surfaces retraction and open-access status, and turns scholarly identifiers (DOI, PMID, PMCID, ISBN, ISSN, arXiv, ADS bibcode, WHO IRIS URL) into formatted citations. Use verifyCitation when the question is 'is this citation real?' — it cross-checks the claimed title against the record the identifier actually resolves to, catching the dominant AI fabrication pattern (real, resolvable DOI + invented title; Topaz et al., Lancet 2026). Such citations resolve cleanly under doi.org, so resolveIdentifier alone NEVER catches them: if you are about to reassure a user that a citation is genuine because its identifier resolves, call verifyCitation first. Use auditBibliography to run that same check across a WHOLE bibliography (BibTeX / RIS / CSL-JSON, or a claims[] array) in one call — per-entry verdict + retraction, plus a corpus summary. Then: checkRetraction for retraction/correction/expression-of-concern status; checkOpenAccess for the best legal open-access copy; resolveIdentifier for structured CSL-JSON metadata on a known-good identifier; formatCitation for a formatted reference in any of 10,000+ styles; exportCitation for bibliography files (BibTeX, RIS, EndNote, CSV, …). All tools are read-only. Works anonymously with no key; an optional free ssk_ bearer key raises rate limits.",
"tools": [
{
"description": "Verify a WHOLE bibliography in one call — the batch counterpart to verifyCitation. Each entry runs the same fabrication check (real, resolvable identifier paired with a title that does NOT match the resolved paper; Topaz et al., Lancet 2026) plus a retraction lookup, and the tool returns a per-entry verdict table and a corpus summary. Use when the user pastes a reference list, a .bib / .ris file, or asks to 'check all these citations at once' / 'audit my bibliography' / 'which of these references are fake or retracted'. Input: EITHER `bibliography` (raw BibTeX / RIS / CSL-JSON text — format auto-detected) OR `claims` (an array of pre-parsed {title + identifier} objects), not both. Capped at 25 entries per call; excess is dropped and reported via `truncated`. `checks` defaults to ['retraction'] (pass [] to skip); `screenWithLlm` opt-in per entry (same auth gating as verifyCitation). Returns: { format, entries: [{ index, sourceKey?, status: 'ok'|'error', verdict: 'matched' | 'mismatch' | 'not_found' | 'ambiguous', confidence, matched, mismatches, retraction: { checked, doi, isRetracted, hasCorrections, hasConcern, notices } | null, _provenance }], parseErrors: [{ index, error, message }], truncated, summary: { total, matched, mismatch, ambiguous, not_found, errored, retracted } }. Reading the result: `index` is 1-BASED (entry 1 is the first reference) — do not add 1 again when reporting it. `sourceKey` is the entry's own key in the source file (BibTeX cite key, RIS `ID`, CSL-JSON `id`) and is the reliable way to point a user at the offending reference; it is absent on the claims[] path. `entries` and `parseErrors` share one index space, so a given input position appears in exactly one of them — report parseErrors as UNCHECKED, never as clean. `summary.total` counts verifiable entries only, excluding parseErrors and anything past the cap; `summary.retracted` is a separate axis from the verdict counts (an entry can be both matched and retracted), so never sum those fields. A non-zero `truncated` means the audit is incomplete — split the bibliography and call again. Per-entry leniency: one entry that fails to resolve becomes status:'error' without failing the batch. This audits citation IDENTITY (does each identifier resolve to the claimed work, and is it retracted) — it does NOT check whether a source supports the claim it is cited for. Read-only and idempotent. Works anonymously for the non-LLM path; SCHOLAR_API_KEY (a free ssk_ key from https://scholar-sidekick.com/account) or a paid RapidAPI tier raises rate limits and enables the optional LLM screen.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"bibliography": {
"description": "Raw bibliography text to parse and audit — BibTeX, RIS, or CSL-JSON. Provide EITHER this or `claims`, not both. Format is auto-detected from the content; override with `format`. Capped at 25 entries per call (excess is dropped and reported via `truncated`).",
"maxLength": 131072,
"type": "string"
},
"checks": {
"description": "Per-entry enrichment checks. Defaults to ['retraction'] (flags retracted / corrected / expression-of-concern works via Crossref + Retraction Watch, keyed on each resolved DOI). Pass [] to skip the retraction lookup.",
"items": {
"enum": [
"retraction"
],
"type": "string"
},
"type": "array"
},
"claims": {
"description": "Pre-parsed citations to audit — an alternative to `bibliography` for agents that already hold structured references. Each needs a `title` plus whatever identifiers the citation carries.",
"items": {
"properties": {
"ads": {
"description": "NASA ADS bibcode, e.g. '2019A&A...625A.135L'.",
"maxLength": 50,
"type": "string"
},
"arxiv": {
"description": "arXiv ID, e.g. '2301.00001' or 'arXiv:2301.00001'.",
"maxLength": 50,
"type": "string"
},
"author": {
"description": "First-author family name as cited. Refines the comparison; a disagreement here can downgrade a verdict to 'ambiguous'.",
"maxLength": 200,
"type": "string"
},
"container": {
"description": "Journal or book title as cited. Refinement only, same role as `year`.",
"maxLength": 500,
"type": "string"
},
"doi": {
"description": "DOI as cited, with or without a prefix ('10.1038/nphys1170' or a doi.org URL).",
"maxLength": 200,
"type": "string"
},
"isbn": {
"description": "ISBN-10 or ISBN-13; hyphens are tolerated.",
"maxLength": 50,
"type": "string"
},
"issn": {
"description": "ISSN of the containing journal. Identifies a container, not a paper, so it cannot resolve an entry on its own — supply it alongside another identifier.",
"maxLength": 50,
"type": "string"
},
"pmcid": {
"description": "PubMed Central ID, e.g. 'PMC1234567'.",
"maxLength": 50,
"type": "string"
},
"pmid": {
"description": "PubMed ID, digits only or 'PMID:' prefixed.",
"maxLength": 50,
"type": "string"
},
"title": {
"description": "Title exactly as the citation claims it. Required — the audit compares this against the title of the record the identifier actually resolves to, and that comparison is the fabrication check.",
"maxLength": 2000,
"type": "string"
},
"whoIrisUrl": {
"description": "WHO IRIS publication URL.",
"maxLength": 2000,
"type": "string"
},
"year": {
"description": "Publication year as cited. Refinement only — it never decides a verdict alone.",
"maximum": 9999,
"minimum": 0,
"type": "integer"
}
},
"required": [
"title"
],
"type": "object"
},
"maxItems": 25,
"type": "array"
},
"format": {
"description": "Override format auto-detection for `bibliography`.",
"enum": [
"bibtex",
"ris",
"csl-json"
],
"type": "string"
},
"screenWithLlm": {
"description": "Opt-in Stage 3 LLM screen applied per entry (same gating as verifyCitation: authenticated first-party key or paid RapidAPI tier). Default false.",
"type": "boolean"
}
},
"type": "object"
},
"name": "auditBibliography",
"outputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"entries": {
"description": "One result per verifiable entry: { index, sourceKey?, status: 'ok'|'error', verdict, confidence, matched, mismatches, retraction, _provenance }. `index` is 1-BASED and counts position in the submitted input, so entry 1 is the first reference — do not add 1 again when you report it to a user. `sourceKey` is the entry's own key in the source file (BibTeX cite key, RIS `ID`, or CSL-JSON `id`) and is the reliable way to map a verdict back to the user's bibliography; it is absent on the claims[] path and on formats that carry no key. `status:'error'` means that one entry failed to verify, not that the batch failed. Entries appear in input order.",
"items": {
"additionalProperties": {},
"propertyNames": {
"type": "string"
},
"type": "object"
},
"type": "array"
},
"format": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Detected input format ('bibtex' | 'ris' | 'csl-json'), or null for the claims[] path."
},
"parseErrors": {
"description": "Entries that could not be parsed or lacked a title: { index, error, message }. Same 1-based `index` space as `entries`, so the two arrays never collide: a given input position appears in exactly one of them. Report these to the user as unchecked, NOT as clean.",
"items": {
"additionalProperties": {},
"propertyNames": {
"type": "string"
},
"type": "object"
},
"type": "array"
},
"summary": {
"additionalProperties": {},
"description": "Corpus roll-up: { total, matched, mismatch, ambiguous, not_found, errored, retracted }. `total` counts verifiable entries only, so it excludes `parseErrors` and anything past the cap. `retracted` is a separate axis from the verdict counts, and an entry can be both matched and retracted — never add the fields together.",
"propertyNames": {
"type": "string"
},
"type": "object"
},
"truncated": {
"description": "Count of entries dropped beyond the 25-entry cap. Non-zero means the audit is incomplete — split the bibliography and call again for the rest.",
"type": "number"
}
},
"type": "object"
}
},
{
"description": "Check whether a single scholarly work is openly accessible and where to find the best legal version. Use when the user asks 'is this open access?', 'where can I read this for free?', or wants the OA license/version before reusing or redistributing. Sourced from Unpaywall. Resolves DOI/PMID/PMCID/arXiv/ISBN/ADS inputs to a DOI before lookup; inputs that don't map to a DOI return doi=null and reason='no_doi'. arXiv inputs check the linked published-journal DOI when arXiv records one; a preprint without one returns doi=null and reason='no_doi' (Unpaywall does not index arXiv preprints, which are freely readable on arXiv regardless). Single identifier per call — does NOT accept comma/newline batches; loop one call per identifier for multiple papers. Returns: { doi, resolvedFrom?, reason?, result } where result has isOa (boolean), oaStatus ('gold' | 'green' | 'hybrid' | 'bronze' | 'closed'), title, bestLocation ({url, hostType: 'publisher' | 'repository', license, version: 'submittedVersion' | 'acceptedVersion' | 'publishedVersion'} or null), and locations (array of the same shape); result is null when no DOI could be resolved and reason explains why ('no_doi'). No sibling tool overlaps this — resolveIdentifier returns metadata but not OA status. Read-only and idempotent — safe to retry. Works anonymously against the public Scholar Sidekick API (rate-limited free tier); set SCHOLAR_API_KEY (a free ssk_ key from https://scholar-sidekick.com/account) for higher limits, or RAPIDAPI_KEY for paid RapidAPI tiers. Rate limits follow your tier; Unpaywall is queried server-side with its own caching.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"id": {
"description": "A single scholarly identifier to check. 1–500 characters. Non-DOI inputs are resolved to a DOI server-side before the lookup; if no DOI can be derived, the tool returns doi=null with reason='no_doi'. Pass exactly one identifier — comma/newline batches are NOT accepted by this tool; loop one call per identifier for multiple papers. Accepted: DOI, PMID, PMCID, arXiv ID, ISBN, or NASA ADS bibcode (with or without prefixes).",
"maxLength": 500,
"minLength": 1,
"type": "string"
}
},
"required": [
"id"
],
"type": "object"
},
"name": "checkOpenAccess",
"outputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"doi": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"reason": {
"type": "string"
},
"resolvedFrom": {
"additionalProperties": false,
"properties": {
"type": {
"type": "string"
},
"value": {
"type": "string"
}
},
"required": [
"type",
"value"
],
"type": "object"
},
"result": {
"anyOf": [
{
"additionalProperties": false,
"properties": {
"bestLocation": {
"anyOf": [
{
"additionalProperties": {},
"propertyNames": {
"type": "string"
},
"type": "object"
},
{
"type": "null"
}
]
},
"isOa": {
"type": "boolean"
},
"locations": {
"items": {
"additionalProperties": {},
"propertyNames": {
"type": "string"
},
"type": "object"
},
"type": "array"
},
"oaStatus": {
"enum": [
"gold",
"green",
"hybrid",
"bronze",
"closed"
],
"type": "string"
},
"title": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
}
},
"type": "object"
},
{
"type": "null"
}
],
"description": "Open-access status, or null when no DOI resolved."
}
},
"required": [
"doi",
"result"
],
"type": "object"
}
},
{
"description": "Check whether a single scholarly work has been retracted, corrected, or had an expression of concern raised. Use when the user asks 'has this paper been retracted?' or wants to verify a paper's standing before citing it (clinical, regulatory, evidence-synthesis contexts). For multi-paper bibliography audits (clinical guidelines, systematic reviews), loop one call per identifier — the tool intentionally rejects batch input to keep retraction-status results unambiguous per work. Sourced from Crossref `updated-by` (which mirrors Retraction Watch). Resolves DOI/PMID/PMCID/arXiv/ADS inputs to a DOI before lookup; ISBN inputs always return doi=null and reason='no_doi' since books are not in the retraction graph. arXiv inputs check the linked published-journal DOI when arXiv records one; a preprint without one returns doi=null and reason='no_doi' (preprints are outside the Crossref retraction graph — arXiv marks withdrawals on the abstract page instead). Single identifier per call — does NOT accept comma/newline batches; loop one call per identifier for multiple papers. Returns: { doi, resolvedFrom?, reason?, result } where result has isRetracted, hasCorrections, hasConcern (booleans), notices (array of {type, label, doi, date, source} where type is a raw Crossref update type such as 'retraction', 'correction', 'erratum' or 'expression_of_concern'), and title; result is null when no DOI could be resolved and reason explains why ('no_doi'). No sibling tool overlaps this — resolveIdentifier returns metadata but not retraction status. Read-only and idempotent — safe to retry. Works anonymously against the public Scholar Sidekick API (rate-limited free tier); set SCHOLAR_API_KEY (a free ssk_ key from https://scholar-sidekick.com/account) for higher limits, or RAPIDAPI_KEY for paid RapidAPI tiers. Rate limits follow your tier; Crossref is queried server-side with its own caching.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"id": {
"description": "A single scholarly identifier to check. 1–500 characters. Non-DOI inputs are resolved to a DOI server-side before the lookup; if no DOI can be derived, the tool returns doi=null with reason='no_doi'. Pass exactly one identifier — comma/newline batches are NOT accepted by this tool; loop one call per identifier for multiple papers. Accepted: DOI, PMID, PMCID, arXiv ID, or NASA ADS bibcode (with or without prefixes). ISBN inputs are accepted but always return doi=null since books are not in the retraction graph.",
"maxLength": 500,
"minLength": 1,
"type": "string"
}
},
"required": [
"id"
],
"type": "object"
},
"name": "checkRetraction",
"outputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"doi": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Resolved DOI, or null when none could be derived."
},
"reason": {
"description": "Why result is null (e.g. 'no_doi').",
"type": "string"
},
"resolvedFrom": {
"additionalProperties": false,
"properties": {
"type": {
"type": "string"
},
"value": {
"type": "string"
}
},
"required": [
"type",
"value"
],
"type": "object"
},
"result": {
"anyOf": [
{
"additionalProperties": false,
"properties": {
"hasConcern": {
"type": "boolean"
},
"hasCorrections": {
"type": "boolean"
},
"isRetracted": {
"type": "boolean"
},
"notices": {
"items": {
"additionalProperties": {},
"propertyNames": {
"type": "string"
},
"type": "object"
},
"type": "array"
},
"title": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
}
},
"type": "object"
},
{
"type": "null"
}
],
"description": "Retraction status, or null when no DOI resolved."
}
},
"required": [
"doi",
"result"
],
"type": "object"
}
},
{
"description": "Export scholarly identifiers to a bibliography file format ready to write to disk or paste into a reference manager. Use when the user wants a file (.bib, .ris, .nbib, .xml, .rdf, .csv) for Zotero, Mendeley, EndNote, RefWorks, BibTeX/LaTeX, Pandoc, or Excel. Format parameter is required: bib (BibTeX — LaTeX), ris (RIS — most widely supported by reference managers), csl (CSL JSON — Pandoc/Quarto), endnote-xml, endnote-refer, refworks, medline (NBIB — PubMed round-trips, clinical workflows), zotero-rdf, csv (spreadsheet-friendly), or txt (plain-text bibliography rendered with the optional style parameter — txt is the only format that uses style; the others have their own structured shape and ignore it). Accepts the same identifier formats as resolveIdentifier (DOI/PMID/PMCID/ISBN/arXiv/ISSN/ADS/WHO IRIS, prefixes tolerated), single or comma/newline-separated batch — one round trip per call. Returns: { content: string, format: string } where content is the entire bibliography in the requested format as a single string — write it to a file (.bib/.ris/.nbib/etc.) or paste it directly into the target tool. Use formatCitation instead when the user wants in-line citation text (manuscript, slide); use resolveIdentifier when they want raw structured metadata. Read-only and idempotent — safe to retry. Works anonymously against the public Scholar Sidekick API (rate-limited free tier); set SCHOLAR_API_KEY (a free ssk_ key from https://scholar-sidekick.com/account) for higher limits, or RAPIDAPI_KEY for paid RapidAPI tiers. Rate limits follow your tier.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"format": {
"description": "Export format",
"enum": [
"bib",
"ris",
"csv",
"csl",
"endnote-refer",
"endnote-xml",
"refworks",
"medline",
"zotero-rdf",
"txt"
],
"type": "string"
},
"lang": {
"description": "Locale for formatting (e.g. en-US)",
"type": "string"
},
"style": {
"description": "Citation style (used only for txt export)",
"type": "string"
},
"text": {
"description": "One or more identifiers (DOIs, PMIDs, ISBNs, etc.) separated by newlines or commas",
"type": "string"
}
},
"required": [
"text",
"format"
],
"type": "object"
},
"name": "exportCitation",
"outputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"content": {
"description": "The entire bibliography in the requested format, as one string.",
"type": "string"
},
"format": {
"description": "The export format that was produced.",
"type": "string"
}
},
"required": [
"content",
"format"
],
"type": "object"
}
},
{
"description": "Format scholarly identifiers into a finished citation in a specific style. Use when the user wants a paste-ready citation string for a manuscript, slide, message, footnote, or in-line reference. Style defaults to vancouver if unspecified; ask the user before defaulting if any ambiguity exists (e.g. 'Harvard' and 'Chicago' have multiple variants — confirm which one). Supports five hand-tuned builtins (vancouver, ama, apa, ieee, cse) plus any of 10,000+ CSL style IDs (chicago-author-date, harvard-cite-them-right, modern-language-association, nature, bmj, the-lancet, etc.). Alias and dependent-style resolution apply, so 'harvard' resolves to 'harvard-cite-them-right' and the canonical ID is reported back as styleUsed. Output defaults to text; pass output=html for marked-up HTML or output=json for structured CSL items. Accepts the same identifier formats as resolveIdentifier (DOI/PMID/PMCID/ISBN/arXiv/ISSN/ADS/WHO IRIS, prefixes tolerated), single or comma/newline-separated batch — one round trip per call. Returns: one of { text, html, items } depending on the output parameter, followed by a metadata block ({formatter: 'builtin' | 'csl', styleUsed, requestId, warnings?}) appended as a second text content item — surface this to the user when they care about reproducibility. Use resolveIdentifier instead when the user wants raw metadata to inspect or transform; use exportCitation when they want a downloadable bibliography file. Read-only and idempotent — safe to retry. Works anonymously against the public Scholar Sidekick API (rate-limited free tier); set SCHOLAR_API_KEY (a free ssk_ key from https://scholar-sidekick.com/account) for higher limits, or RAPIDAPI_KEY for paid RapidAPI tiers. Rate limits follow your tier.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"footnote": {
"description": "Format as footnotes instead of bibliography entries",
"type": "boolean"
},
"lang": {
"description": "Locale for formatting (e.g. en-US, en-GB, fr-FR)",
"type": "string"
},
"output": {
"description": "Output format (default: text)",
"enum": [
"text",
"html",
"json"
],
"type": "string"
},
"style": {
"description": "Citation style: vancouver (default), ama, apa, ieee, cse, or any CSL style ID",
"type": "string"
},
"text": {
"description": "One or more identifiers (DOIs, PMIDs, ISBNs, arXiv IDs, etc.) separated by newlines or commas",
"type": "string"
}
},
"required": [
"text"
],
"type": "object"
},
"name": "formatCitation",
"outputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"formatter": {
"description": "Which engine formatted: 'builtin' or 'csl'.",
"type": "string"
},
"html": {
"description": "Formatted citation HTML (when output=html).",
"type": "string"
},
"items": {
"description": "Structured CSL items (when output=json).",
"items": {
"additionalProperties": {},
"propertyNames": {
"type": "string"
},
"type": "object"
},
"type": "array"
},
"lang": {
"description": "Locale used for formatting.",
"type": "string"
},
"styleUsed": {
"description": "Canonical style ID after alias/dependent-style resolution.",
"type": "string"
},
"text": {
"description": "Formatted citation text (when output=text).",
"type": "string"
},
"warnings": {
"items": {
"type": "string"
},
"type": "array"
}
},
"type": "object"
}
},
{
"description": "Resolve scholarly identifiers to structured CSL JSON metadata (title, authors, journal, year, identifiers). Use when the user wants raw bibliographic data to inspect, transform, or feed into another tool — not a formatted citation. Common single-shot conversions: PMID → PMCID, arXiv → DOI, ISBN → CSL JSON, WHO IRIS URL → structured metadata. Accepts DOI, PMID, PMCID, ISBN, arXiv ID, ISSN, NASA ADS bibcode, or WHO IRIS URL, with or without prefixes (PMID:, arXiv:, ISBN hyphens, https://doi.org/...). Pass a single identifier or a comma/newline-separated batch — one round trip per call. Returns: a JSON array of CSL items, each with id, type, title, author[], issued.date-parts, container-title, DOI/PMID/PMCID/ISBN/ISSN/URL when available. Use formatCitation instead when the user wants a finished citation string in a specific style; use exportCitation when they want a downloadable bibliography file. Read-only and idempotent — safe to retry. Works anonymously against the public Scholar Sidekick API (rate-limited free tier); set SCHOLAR_API_KEY (a free ssk_ key from https://scholar-sidekick.com/account) for higher limits, or RAPIDAPI_KEY for paid RapidAPI tiers. Rate limits follow your tier; the underlying REST API caches repeated identical requests and surfaces cache state in the x-scholar-cache response header.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"text": {
"description": "One or more identifiers to resolve (DOIs, PMIDs, PMCIDs, ISBNs, arXiv IDs, ISSNs, ADS bibcodes) separated by newlines or commas",
"type": "string"
}
},
"required": [
"text"
],
"type": "object"
},
"name": "resolveIdentifier",
"outputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"items": {
"description": "Resolved CSL JSON items, one per identifier.",
"items": {
"additionalProperties": {},
"propertyNames": {
"type": "string"
},
"type": "object"
},
"type": "array"
}
},
"required": [
"items"
],
"type": "object"
}
},
{
"description": "Verify a claimed citation against the resolved record at its identifier. Detects the dominant AI-driven fabrication pattern documented by Topaz et al. (Lancet 2026): a real, resolvable identifier (DOI / PMID / PMCID / arXiv / etc.) paired with a title that does NOT correspond to the paper at that identifier. Use when the user pastes a citation and asks 'is this real?' or 'check this DOI' — most fabricated citations resolve cleanly under doi.org but their cited title and the resolved title disagree. Single citation per call. Required: `title` plus exactly one identifier (doi, pmid, pmcid, isbn, arxiv, issn, ads, or whoIrisUrl). Optional refinements: author (first-author family name), year, container (journal). Set `screenWithLlm: true` to invoke the Stage 3 LLM screen on low-confidence mismatches (catches informal-abbreviation false positives); LLM access is gated to authenticated first-party keys and paid RapidAPI tiers — anonymous callers get 400 LLM_SCREEN_FORBIDDEN. Returns: { verdict: 'matched' | 'mismatch' | 'not_found' | 'ambiguous', confidence: 'high' | 'medium' | 'low', matched: <resolved record or null>, mismatches: [{field, claimed, resolved, similarity}], candidates: [{item, registries, score}] (when title-search ran), _provenance: {stages_run, resolved_via, registries_searched, llm_screen} }. Verdict semantics: 'matched' = claim agrees with resolved record; 'mismatch' = identifier resolves but title does not match (Topaz fabrication pattern); 'ambiguous' = identifier resolves to one paper but the claimed title matches a DIFFERENT paper found via title-search (CITADEL 'citation error' subtype — wrong identifier for a real paper); 'not_found' = neither the identifier nor the title resolves anywhere. No sibling tool overlaps: resolveIdentifier returns metadata for a known-good identifier; verifyCitation is the only tool that cross-checks claimed title vs resolved metadata. Read-only and idempotent — safe to retry. Works anonymously for the non-LLM path; the Stage 3 LLM screen requires authentication — set SCHOLAR_API_KEY (a free ssk_ key from https://scholar-sidekick.com/account) or use a paid RapidAPI tier. SCHOLAR_API_KEY also raises your rate limit.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"ads": {
"description": "NASA ADS bibcode (19 chars).",
"maxLength": 50,
"type": "string"
},
"arxiv": {
"description": "arXiv ID (e.g. '2301.08745' or 'arXiv:2301.08745'; old-style 'hep-ph/0501023' accepted).",
"maxLength": 50,
"type": "string"
},
"author": {
"description": "First-author family name as cited. Refines the verdict — a title-vs-resolved-title match plus an author mismatch raises suspicion of fabrication. Pass only the family name (e.g. 'Topaz', not 'Topaz, Maxim').",
"maxLength": 200,
"type": "string"
},
"container": {
"description": "Journal or container name as cited (e.g. 'The Lancet', 'Neuroscience'). Soft signal — surfaced as a mismatch field but does not gate the verdict.",
"maxLength": 500,
"type": "string"
},
"doi": {
"description": "DOI as cited (with or without https://doi.org/ prefix). Provide whichever identifier(s) the cited reference carries; the verifier uses the first one in priority order doi > pmid > pmcid > arxiv > ads > isbn > issn > whoIrisUrl.",
"maxLength": 200,
"type": "string"
},
"isbn": {
"description": "ISBN (10- or 13-digit, hyphens tolerated).",
"maxLength": 50,
"type": "string"
},
"issn": {
"description": "ISSN for journal-level resolution.",
"maxLength": 50,
"type": "string"
},
"pmcid": {
"description": "PubMed Central ID (e.g. 'PMC1234567' or 'PMCID:1234567').",
"maxLength": 50,
"type": "string"
},
"pmid": {
"description": "PubMed ID as cited (digits only, or with 'PMID:' prefix).",
"maxLength": 50,
"type": "string"
},
"screenWithLlm": {
"description": "Opt-in Stage 3 LLM screen. Fires only when the pre-LLM verdict is mismatch with low confidence (the informal-abbreviation false-positive bucket). Gated: requires an authenticated first-party API key or a paid RapidAPI tier; anonymous / free callers receive 400 LLM_SCREEN_FORBIDDEN. Default false.",
"type": "boolean"
},
"title": {
"description": "The title as it appears in the cited reference. This is the field the verifier cross-checks against the resolved record at the supplied identifier. Required.",
"maxLength": 2000,
"minLength": 1,
"type": "string"
},
"whoIrisUrl": {
"description": "WHO IRIS URL (https://iris.who.int/...).",
"maxLength": 2000,
"type": "string"
},
"year": {
"description": "Publication year as cited. Wrong year alone does not flip the verdict, but >=2-year gap from the resolved record lowers confidence.",
"maximum": 9999,
"minimum": 0,
"type": "integer"
}
},
"required": [
"title"
],
"type": "object"
},
"name": "verifyCitation",
"outputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"_provenance": {
"additionalProperties": {},
"propertyNames": {
"type": "string"
},
"type": "object"
},
"candidates": {
"items": {
"additionalProperties": {},
"propertyNames": {
"type": "string"
},
"type": "object"
},
"type": "array"
},
"confidence": {
"enum": [
"high",
"medium",
"low"
],
"type": "string"
},
"matched": {
"anyOf": [
{
"additionalProperties": {},
"propertyNames": {
"type": "string"
},
"type": "object"
},
{
"type": "null"
}
],
"description": "The resolved record at the identifier, or null on not_found."
},
"mismatches": {
"items": {
"additionalProperties": {},
"propertyNames": {
"type": "string"
},
"type": "object"
},
"type": "array"
},
"verdict": {
"enum": [
"matched",
"mismatch",
"not_found",
"ambiguous"
],
"type": "string"
}
},
"type": "object"
}
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:0f1a8c057b61b2f98a35a6464a38f84de66dbed823c62b56ed728cde12ec1bde | sha256sum