Resolve scholarly identifiers (DOI, PMID, ISBN, arXiv, ISSN, ADS, WHO IRIS) into citations (10,000+ CSL styles) and exports (BibTeX, RIS, EndNote...), plus retraction, open-access, and citation-fabrication checks. Six tools, anonymous-friendly Streamable HTTP.
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Average 4.8/5 across 6 of 6 tools scored.
Each tool targets a distinct function: OA status, retraction status, identifier resolution, citation formatting, citation export, and citation verification. There is no overlap in purpose.
All tool names follow a consistent verb_noun pattern with camelCase (e.g., checkOpenAccess, resolveIdentifier). No mixing of styles.
Six tools is well-scoped for a scholarly citation server. Each tool serves a clear need without being excessive or insufficient.
The tool set covers core tasks: lookup, verification, formatting, and export. Missing a search or discovery tool, but that's outside the stated purpose.
auditBibliographyAudit BibliographyAVerify 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 } }. 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.
| Name | Required | Description | Default |
|---|---|---|---|
| checks | No | 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. | |
| claims | No | 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. | |
| format | No | Override format auto-detection for `bibliography`. | |
| bibliography | No | 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`). | |
| screenWithLlm | No | Opt-in Stage 3 LLM screen applied per entry (same gating as verifyCitation: authenticated first-party key or paid RapidAPI tier). Default false. |
| Name | Required | Description |
|---|---|---|
| format | No | Detected input format ('bibtex' | 'ris' | 'csl-json'), or null for the claims[] path. |
| entries | No | One result per verifiable entry: { index, sourceKey?, status: 'ok'|'error', verdict, confidence, matched, mismatches, retraction, _provenance }. |
| summary | No | Corpus roll-up: { total, matched, mismatch, ambiguous, not_found, errored, retracted }. |
| truncated | No | Count of entries dropped beyond the 25-entry cap. |
| parseErrors | No | Entries that could not be parsed or lacked a title: { index, error, message }. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds significant context beyond these: it is read-only and idempotent, works anonymously for non-LLM path, details authentication requirements, per-entry leniency (one error doesn't fail batch), truncation behavior, and clarifies it checks identity not support.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is lengthy but well-structured, starting with the main purpose, then input options, behavior, and return format. Every sentence serves a purpose, though some details (e.g., specific fabrication check example) could be slightly trimmed without losing clarity. Overall it is efficient for the complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (batch audit, multiple input formats, optional LLM screen, truncation, retraction lookup), the description covers all essential aspects: input, behavior, limitations, authentication, and return format. The output schema is also provided, so return values are fully documented. No gaps remain.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with each parameter described. The description adds meaning beyond schema: explains 'bibliography' vs 'claims' mutual exclusivity, default for 'checks' and effect of skipping, and that 'screenWithLlm' has same auth gating as verifyCitation. This adds value, justifying a score above baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it is the batch counterpart to verifyCitation for auditing entire bibliographies, specifying it checks fabrication (real identifier with non-matching title) and retractions. It distinguishes from siblings like verifyCitation (single) and checkRetraction by noting its batch nature and scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly describes when to use: when user pastes a reference list, .bib/.ris file, or asks to 'check all these citations at once'. It also specifies input options (bibliography text or claims array) and the 25-entry cap. While it doesn't state when not to use, it provides clear context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
checkOpenAccessCheck Open AccessACheck 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'. 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.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | 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). |
| Name | Required | Description |
|---|---|---|
| doi | Yes | |
| reason | No | |
| result | Yes | Open-access status, or null when no DOI resolved. |
| resolvedFrom | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint, idempotentHint), adds details: resolution behavior for non-DOI inputs, response structure with reason for failure, rate limits, API key options, and caching. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Long but well-structured; every sentence adds value. Front-loaded with purpose and usage. Slightly verbose but not wasteful. Could trim some details but still efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers all necessary aspects: purpose, usage, behavior, output schema (even though output schema exists), error handling, authentication, rate limits. Complete for a tool with input resolution and multiple output fields.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but description adds significant semantics: explains resolution process, accepted identifier types, rejection of batches, and behavior when no DOI is found. Greatly enhances agent understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool checks OA status and best location, with specific verb 'check'. Explicitly distinguishes from sibling tool 'resolveIdentifier' by stating it returns metadata but not OA status.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit when-to-use examples ('is this open access?', 'where can I read for free?'), tells when not to use (single identifier only, no batches), and mentions sibling alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
checkRetractionCheck RetractionACheck 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. 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.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | 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. |
| Name | Required | Description |
|---|---|---|
| doi | Yes | Resolved DOI, or null when none could be derived. |
| reason | No | Why result is null (e.g. 'no_doi'). |
| result | Yes | Retraction status, or null when no DOI resolved. |
| resolvedFrom | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint. The description adds context: read-only and idempotent (safe to retry), data source (Crossref updated-by mirroring Retraction Watch), ISBN special case (always no_doi), rate limits and API key usage. No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is quite detailed but well-structured: front-loaded purpose, followed by usage guidance, behavioral details, and API key info. While longer than ideal, the complexity of the tool (multiple identifier types, batch restrictions, rate limits) justifies the length. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has one parameter, good annotations, and a described output schema, the description completely covers all necessary information: input format, batch behavior, special cases (ISBN), return shape, rate limits, and authentication. No gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema describes the 'id' parameter with length, accepted formats, and batch behavior. The description adds further semantics: it resolves non-DOI identifiers to DOI before lookup, ISBN always returns no_doi, and explains the resolution behavior. Schema coverage is 100%.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool checks for retraction, correction, or expression of concern on a single work. It explicitly distinguishes from siblings by stating 'No sibling tool overlaps this' and citing resolveIdentifier as a non-overlapping alternative.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit when-to-use scenarios (e.g., user asks 'has this paper been retracted?', clinical/regulatory/evidence-synthesis contexts) and when-not-to-use (rejects batch input, must loop for multiple papers). Also clarifies that for multi-paper audits, one should loop per identifier.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
exportCitationExport CitationAExport 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.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | Locale for formatting (e.g. en-US) | |
| text | Yes | One or more identifiers (DOIs, PMIDs, ISBNs, etc.) separated by newlines or commas | |
| style | No | Citation style (used only for txt export) | |
| format | Yes | Export format |
| Name | Required | Description |
|---|---|---|
| format | Yes | The export format that was produced. |
| content | Yes | The entire bibliography in the requested format, as one string. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint and idempotentHint. The description adds rate limits, API key tiers, batch behavior (one round trip per call), and retry safety—all without contradicting annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but packed with useful information, front-loading the main purpose. Every sentence adds value, though it could be slightly more concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (4 params, enum, output schema), the description thoroughly covers usage, return format, API keys, and retry safety. It is complete enough for an agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds significant value by explaining each enum value for format (e.g., 'ris' is widely supported), that style only works with txt, and that text accepts same identifier formats as resolveIdentifier.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool exports scholarly identifiers to bibliography files with specific formats and use cases. It distinguishes from siblings like formatCitation and resolveIdentifier.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use this tool (file export), when to use formatCitation (in-line text), and when to use resolveIdentifier (raw metadata). Also explains batch usage and format parameter requirements.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
formatCitationFormat CitationAFormat 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.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | Locale for formatting (e.g. en-US, en-GB, fr-FR) | |
| text | Yes | One or more identifiers (DOIs, PMIDs, ISBNs, arXiv IDs, etc.) separated by newlines or commas | |
| style | No | Citation style: vancouver (default), ama, apa, ieee, cse, or any CSL style ID | |
| output | No | Output format (default: text) | |
| footnote | No | Format as footnotes instead of bibliography entries |
| Name | Required | Description |
|---|---|---|
| html | No | Formatted citation HTML (when output=html). |
| lang | No | Locale used for formatting. |
| text | No | Formatted citation text (when output=text). |
| items | No | Structured CSL items (when output=json). |
| warnings | No | |
| formatter | No | Which engine formatted: 'builtin' or 'csl'. |
| styleUsed | No | Canonical style ID after alias/dependent-style resolution. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint, idempotentHint), adds idempotency detail, API key requirements, rate limits, and return structure including a metadata block.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Fairly long but well-structured with front-loaded purpose. Every sentence adds value, though could be slightly tightened without losing content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers all aspects: usage context, parameter details, output structure, API keys, rate limits, and distinguishes from siblings. Complete given complexity and existing output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Adds significant meaning beyond schema: explains default style, alias resolution, batch processing, output options, and example CSL IDs. Schema coverage is 100% but description greatly enhances understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Describes a specific verb (format) and resource (scholarly identifiers into a finished citation) and clearly distinguishes from siblings like resolveIdentifier and exportCitation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use ('paste-ready citation string') and when not to use alternatives, and advises to ask user before defaulting style if ambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
resolveIdentifierResolve IdentifierAResolve 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.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | One or more identifiers to resolve (DOIs, PMIDs, PMCIDs, ISBNs, arXiv IDs, ISSNs, ADS bibcodes) separated by newlines or commas |
| Name | Required | Description |
|---|---|---|
| items | Yes | Resolved CSL JSON items, one per identifier. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds further context: rate limits, caching, API key usage, and safety characteristics (idempotent, safe to retry). No contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections: purpose, usage, accepted identifiers, output, alternatives, safety, and API info. It is somewhat long but every sentence adds value. Could be slightly tighter.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (multiple identifier types, batch processing, API keys, outputs), the description is fully complete. An output schema exists, so return values are already documented. No gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with one parameter 'text'. The description adds meaning beyond schema by explaining acceptable identifier formats (prefixes, batch handling), which the schema does not specify.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it resolves scholarly identifiers to CSL JSON metadata. It specifies the resource (identifiers) and the output format. It distinguishes from sibling tools like formatCitation and exportCitation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says when to use: when user wants raw bibliographic data, not a formatted citation. It provides alternatives: use formatCitation for finished citation strings, exportCitation for downloadable files.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
verifyCitationVerify CitationAVerify 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.
| Name | Required | Description | Default |
|---|---|---|---|
| ads | No | NASA ADS bibcode (19 chars). | |
| doi | No | 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. | |
| isbn | No | ISBN (10- or 13-digit, hyphens tolerated). | |
| issn | No | ISSN for journal-level resolution. | |
| pmid | No | PubMed ID as cited (digits only, or with 'PMID:' prefix). | |
| year | No | Publication year as cited. Wrong year alone does not flip the verdict, but >=2-year gap from the resolved record lowers confidence. | |
| arxiv | No | arXiv ID (e.g. '2301.08745' or 'arXiv:2301.08745'; old-style 'hep-ph/0501023' accepted). | |
| pmcid | No | PubMed Central ID (e.g. 'PMC1234567' or 'PMCID:1234567'). | |
| title | Yes | 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. | |
| author | No | 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'). | |
| container | No | Journal or container name as cited (e.g. 'The Lancet', 'Neuroscience'). Soft signal — surfaced as a mismatch field but does not gate the verdict. | |
| whoIrisUrl | No | WHO IRIS URL (https://iris.who.int/...). | |
| screenWithLlm | No | 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. |
| Name | Required | Description |
|---|---|---|
| matched | No | The resolved record at the identifier, or null on not_found. |
| verdict | No | |
| candidates | No | |
| confidence | No | |
| mismatches | No | |
| _provenance | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate read-only, idempotent, non-destructive. Description reinforces read-only and idempotent (safe to retry), explains authentication gates for LLM screen, and describes verdict semantics. No contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Thorough but slightly lengthy; front-loaded with purpose. Every sentence serves a purpose, but could be trimmed slightly for brevity without losing content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 13 parameters and output schema, description covers all necessary aspects: use cases, authentication, retry safety, verdict semantics, sibling differentiation. Complete and self-contained.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers 100% of parameters, but description adds significant context: identifier priority order, year gap effect on confidence, author format, screenWithLlm gating. Adds value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it verifies a citation by cross-checking title against resolved record, specifically detecting the Topaz fabrication pattern. Distinguishes from sibling tools: resolveIdentifier returns metadata without cross-checking.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly tells when to use (user asks 'is this real?' or 'check this DOI') and single citation per call. Differentiates from resolveIdentifier by noting the cross-checking behavior.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
No comments yet. Be the first to start the discussion!
