Skip to main content
Glama

Scholar Sidekick

by io.github.mlava

Verify Citation

verifyCitation
Read-onlyIdempotent

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: , 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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
adsNoNASA ADS bibcode (19 chars).
doiNoDOI 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.
isbnNoISBN (10- or 13-digit, hyphens tolerated).
issnNoISSN for journal-level resolution.
pmidNoPubMed ID as cited (digits only, or with 'PMID:' prefix).
yearNoPublication year as cited. Wrong year alone does not flip the verdict, but >=2-year gap from the resolved record lowers confidence.
arxivNoarXiv ID (e.g. '2301.08745' or 'arXiv:2301.08745'; old-style 'hep-ph/0501023' accepted).
pmcidNoPubMed Central ID (e.g. 'PMC1234567' or 'PMCID:1234567').
titleYesThe 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.
authorNoFirst-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').
containerNoJournal or container name as cited (e.g. 'The Lancet', 'Neuroscience'). Soft signal — surfaced as a mismatch field but does not gate the verdict.
whoIrisUrlNoWHO IRIS URL (https://iris.who.int/...).
screenWithLlmNoOpt-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.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
matchedNoThe resolved record at the identifier, or null on not_found.
verdictNo
candidatesNo
confidenceNo
mismatchesNo
_provenanceNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, and the description reinforces those traits with 'Read-only and idempotent — safe to retry.' It adds substantial context: the Topaz fabrication pattern, verdict semantics, auth gating for LLM screen (400 LLM_SCREEN_FORBIDDEN for anonymous callers), and rate-limit note. These details go well beyond the annotations and meaningfully inform the agent of real-world behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but front-loaded: the first sentence states the core purpose. Every subsequent sentence adds unique information—detection pattern, usage triggers, parameter rules, LLM gating, return structure, verdict semantics, sibling differentiation, safety. No word is wasted; it is an appropriately sized, information-dense reference.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (13 parameters, multiple identifiers, gated LLM screen), the description is remarkably complete. It explains the full return object, every verdict meaning with example subtypes, authentication requirements, error codes, and idempotency. The output schema exists but is not shown in this definition; the description compensates fully by documenting the return structure and semantics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents every parameter baseline. The description adds value by clarifying the identifier priority order, the requirement of 'title plus exactly one identifier' (even though the schema only marks title as required), the soft-signal nature of container, and the gating of screenWithLlm. This is genuinely helpful, but not exceptional since many parameter details are already in the schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource: 'Verify a claimed citation against the resolved record at its identifier.' It immediately identifies the dominant AI-driven fabrication pattern and clearly distinguishes itself from resolveIdentifier by stating it is the only tool that cross-checks claimed title vs resolved metadata. This is unambiguous and differentiates from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit use-case guidance is provided: 'Use when the user pastes a citation and asks "is this real?" or "check this DOI".' It also states single citation per call, required fields, and explicitly names the alternative tool (resolveIdentifier) for known-good identifiers. The LLM screen usage and authentication requirements are clearly described, leaving no ambiguity about when to invoke this versus siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Scholar Sidekick toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.9/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: auditBibliography is the batch counterpart to verifyCitation, checkOpenAccess focuses on OA status, checkRetraction on retractions, resolveIdentifier returns raw metadata, formatCitation produces citation strings, and exportCitation produces files. Descriptions explicitly cross-reference each other to prevent confusion.

Naming Consistency5/5

All tool names follow a consistent verb_noun camelCase pattern: audit, check, check, export, format, resolve, verify + object. There is no mixing of styles or vague verbs.

Tool Count5/5

With 7 tools, the server is well-scoped for its purpose of citation verification and formatting. Each tool covers a distinct operational need (batch audit, single verify, OA, retraction, format, export, resolve) without bloat.

Completeness5/5

The toolset covers the full citation lifecycle: verifying a single citation, auditing entire bibliographies, checking retraction and open-access status, formatting citations, exporting to common bibliography formats, and resolving identifiers to metadata. No obvious gaps exist for the stated domain.

Resources