Skip to main content
Glama

Get DataCite citation

datacite_get_citation
Read-onlyIdempotent

Render one DataCite DOI as a formatted citation in a CSL style and locale (APA in US English by default), or as a machine-readable record: CSL JSON, BibTeX, RIS, DataCite JSON or XML, Schema.org JSON-LD, Codemeta, or JATS. A style the upstream renderer does not support — an unknown id or a dependent journal style — is rejected instead of silently rendered as APA. Formatted text comes back as plain text alongside the upstream HTML markup. A long document comes back one slice at a time: limit sets the slice size in UTF-16 units (default 100,000) and nextOffset continues it. A DOI DataCite does not hold returns found: false naming the registration agency that does.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "doi": "<doi>"
    },
    "name": "datacite_get_citation"
  }
}

Input Schema

NameRequiredDescriptionDefault
doiYesThe DataCite DOI, e.g. 10.5061/dryad.234. Accepted bare, with doi: or info:doi/ prefixes, as a doi.org / dx.doi.org URL, or %2F-encoded; case-insensitive.
limitNoUTF-16 code units of the document per slice (for text, of the upstream HTML), a positive integer (default 100,000). A slice ends early rather than split a surrogate pair, or for text a tag or character reference, and runs past limit only when one such unit alone is longer. Values above 1,000,000 apply 1,000,000 with a notice unless strict limits are configured.
styleNoCSL style id for format text, e.g. apa (default), ieee, chicago-author-date, modern-language-association, vancouver, nature. Lowercased. A style that would silently fall back to APA is rejected. Verified ids: datacite_list_reference topic citation_styles.
formatNotext (formatted citation, default), csl_json, bibtex, ris, datacite_json, datacite_xml, schema_org, codemeta, or jats.
localeNoCSL locale for format text, e.g. en-GB, de-DE, fr-FR, or a bare language (de → de-DE); any case. Omitted: en-US. List: datacite_list_reference topic citation_locales.
offsetNoZero-based offset, in UTF-16 code units, where the slice starts (for text, into the upstream HTML); default 0. An offset inside a surrogate pair, or for text inside a tag or character reference, starts the slice at that unit's start. Pass nextOffset to continue. At or past the end the slice is empty.

Output Schema

NameRequiredDescriptionDefault
capNoThe limit applied, in UTF-16 code units.
doiNoThe DOI, lowercase.
errorNoPresent when the call failed. Absent on success.
foundNoTrue when DataCite holds the DOI and rendered it; false when it holds no public record (the miss fields explain).
shownNoUTF-16 code units in this slice (for text, of the HTML in citationHtml).
styleNoCSL style applied (text only).
formatNoThe format requested.
localeNoCSL locale applied (text only; absent means en-US).
noticeNoSet when the style could not be confirmed as distinct from APA, JATS contains empty names or inconsistent years, a limit over 1,000,000 was applied as 1,000,000, or citation is a slice of the document (its range and the call that continues it).
citationNotext: the citation as plain text (tags stripped, entities decoded) of the HTML in citationHtml; each slice is converted on its own, so join citationHtml slices, not these, to rebuild a paged text document. Machine formats: the document verbatim, or the slice of it offset and limit select, never splitting a surrogate pair; slices joined in offset order reproduce it exactly. Empty when offset is at or past the end.
guidanceNoThe next step for this miss. Miss arm only.
mediaTypeNoMedia type negotiated. Found only.
truncatedNoTrue when citation is a slice short of the whole document: units remain past it (nextOffset), or offset starts it past the beginning.
missReasonNoWhy DataCite holds no public record: another agency registered it, no agency did, it is a DataCite DOI without public (Findable) metadata, or the agency lookup did not answer. Miss arm only.
nextOffsetNoWhere the next slice starts: call again with the same doi, format, style, locale, and limit, and this as offset. Absent once a slice reaches the end.
downloadUrlNoExact negotiated URL for the whole document, returned with a slice short of it; fetch it to retrieve the document in one response.
citationHtmlNotext only: the upstream HTML markup verbatim (<i>, &amp;, small caps): the whole rendering trimmed, or the exact slice offset and limit select, which never ends inside a tag or character reference.
totalCharactersNoLength of the whole document in UTF-16 code units (for text, of the upstream HTML), returned with a slice short of it.
registrationAgencyNoRegistration agency that holds the DOI (e.g. Crossref, mEDRA, DataCite), when known. Miss arm only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changed
    • addedInput schema / properties / limit
      Added value: +{
      +  "default": 100000,
      +  "description": "UTF-16 code units of the document per slice (for text, of the upstream HTML), a positive integer (default 100,000). A slice ends early rather than split a surrogate pair, or for text a tag or character reference, and runs past limit only when one such unit alone is longer. Values above 1,000,000 apply 1,000,000 with a notice unless strict limits are configured.",
      +  "minimum": 1,
      +  "multipleOf": 1,
      +  "type": "number"
      +}
    • addedInput schema / properties / offset
      Added value: +{
      +  "description": "Zero-based offset, in UTF-16 code units, where the slice starts (for text, into the upstream HTML); default 0. An offset inside a surrogate pair, or for text inside a tag or character reference, starts the slice at that unit's start. Pass nextOffset to continue. At or past the end the slice is empty.",
      +  "maximum": 9007199254740991,
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • changedOutput schema / properties / cap / description
      Previous value: -"The character cap applied: 100,000."New value: +"The limit applied, in UTF-16 code units."
    • changedOutput schema / properties / citation / description
      Previous value: -"text: the citation as plain text (tags stripped, entities decoded), cut at 100,000 upstream UTF-16 units. Machine formats: the complete payload verbatim when at most 100,000 units; otherwise omitted in favor of downloadUrl."New value: +"text: the citation as plain text (tags stripped, entities decoded) of the HTML in citationHtml; each slice is converted on its own, so join citationHtml slices, not these, to rebuild a paged text document. Machine formats: the document verbatim, or the slice of it offset and limit select, never splitting a surrogate pair; slices joined in offset order reproduce it exactly. Empty when offset is at or past the end."
    • changedOutput schema / properties / citationHtml / description
      Previous value: -"text only: the upstream HTML markup verbatim (<i>, &amp;, small caps), cut like citation."New value: +"text only: the upstream HTML markup verbatim (<i>, &amp;, small caps): the whole rendering trimmed, or the exact slice offset and limit select, which never ends inside a tag or character reference."
    • changedOutput schema / properties / downloadUrl / description
      Previous value: -"Exact negotiated URL for the complete machine document when it exceeds the inline cap; fetch this URL to retrieve the document."New value: +"Exact negotiated URL for the whole document, returned with a slice short of it; fetch it to retrieve the document in one response."
    • addedOutput schema / properties / nextOffset
      Added value: +{
      +  "description": "Where the next slice starts: call again with the same doi, format, style, locale, and limit, and this as offset. Absent once a slice reaches the end.",
      +  "type": "number"
      +}
    • changedOutput schema / properties / notice / description
      Previous value: -"Set when the style could not be confirmed as distinct from APA, JATS contains empty names or inconsistent years, or the payload exceeded the inline cap (length and retrieval guidance)."New value: +"Set when the style could not be confirmed as distinct from APA, JATS contains empty names or inconsistent years, a limit over 1,000,000 was applied as 1,000,000, or citation is a slice of the document (its range and the call that continues it)."
    • changedOutput schema / properties / shown / description
      Previous value: -"UTF-16 code units of DataCite's payload kept inline; zero for an oversized machine document, or the units text and citationHtml derive from."New value: +"UTF-16 code units in this slice (for text, of the HTML in citationHtml)."
    • changedOutput schema / properties / totalCharacters / description
      Previous value: -"Complete oversized machine document length in UTF-16 code units."New value: +"Length of the whole document in UTF-16 code units (for text, of the upstream HTML), returned with a slice short of it."
    • changedOutput schema / properties / truncated / description
      Previous value: -"True when the payload exceeded 100,000 UTF-16 code units: text was cut or a machine document was omitted for download."New value: +"True when citation is a slice short of the whole document: units remain past it (nextOffset), or offset starts it past the beginning."
  2. Changed1 schema field changed
    • changedOutput schema / properties / notice / description
      Previous value: -"Set when the style could not be confirmed as distinct from APA, or when the payload exceeded the inline cap (length and retrieval guidance)."New value: +"Set when the style could not be confirmed as distinct from APA, JATS contains empty names or inconsistent years, or the payload exceeded the inline cap (length and retrieval guidance)."
  3. Changed6 schema fields changed
    • changedOutput schema / properties / citation / description
      Previous value: -"text: the citation as plain text (tags stripped, entities decoded); machine formats: the payload verbatim. A payload over 100,000 characters is cut to its first 100,000 (truncated: true)."New value: +"text: the citation as plain text (tags stripped, entities decoded), cut at 100,000 upstream UTF-16 units. Machine formats: the complete payload verbatim when at most 100,000 units; otherwise omitted in favor of downloadUrl."
    • addedOutput schema / properties / downloadUrl
      Added value: +{
      +  "description": "Exact negotiated URL for the complete machine document when it exceeds the inline cap; fetch this URL to retrieve the document.",
      +  "type": "string"
      +}
    • changedOutput schema / properties / notice / description
      Previous value: -"Set when the style could not be confirmed as distinct from APA, or when the payload was cut (its full length and the cut)."New value: +"Set when the style could not be confirmed as distinct from APA, or when the payload exceeded the inline cap (length and retrieval guidance)."
    • changedOutput schema / properties / shown / description
      Previous value: -"Characters of DataCite's payload kept; for text, citation and citationHtml derive from them."New value: +"UTF-16 code units of DataCite's payload kept inline; zero for an oversized machine document, or the units text and citationHtml derive from."
    • addedOutput schema / properties / totalCharacters
      Added value: +{
      +  "description": "Complete oversized machine document length in UTF-16 code units.",
      +  "type": "number"
      +}
    • changedOutput schema / properties / truncated / description
      Previous value: -"True when the payload ran past 100,000 characters and was cut."New value: +"True when the payload exceeded 100,000 UTF-16 code units: text was cut or a machine document was omitted for download."
  4. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/openWorld, and the description adds behavior beyond them: no silent APA fallback for unsupported styles, plain text returned alongside upstream HTML markup, and slice-based pagination via limit/nextOffset. It also discloses the failure mode for DOIs DataCite does not hold.

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

Conciseness4/5

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

Front-loaded with the primary purpose, then formats, then failure modes and pagination — no filler sentences. It is dense, and the repeated reference to 'upstream HTML markup' in both the text and pagination clauses is mildly redundant.

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

Completeness4/5

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

An output schema exists, so return-value explanation is not required, yet the description still covers the important non-obvious outcome (found: false plus agency name) and pagination continuation. For a six-parameter read tool this covers what an agent needs to call it correctly.

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 coverage is 100%, so the schema already carries the field-level detail; the description still adds the conceptual model of limit as a slice size in UTF-16 units and nextOffset as its continuation, plus the default style/locale. It does not go much beyond the schema on doi/format beyond restating the options.

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

Purpose4/5

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

States a specific verb and resource ('Render one DataCite DOI as a formatted citation') and enumerates the output modes (CSL JSON, BibTeX, RIS, DataCite JSON/XML, Schema.org, Codemeta, JATS), so an agent knows exactly what comes back. It does not explicitly contrast itself with datacite_get_work, so the boundary against that sibling must be inferred.

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

Usage Guidelines4/5

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

Gives concrete context: APA/US English are defaults, unknown or dependent styles are rejected, and a non-DataCite DOI yields found: false naming the registration agency. It stops short of naming an alternative tool or an explicit 'use this instead of X' rule.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.