Skip to main content
Glama
Sign In

orcid-mcp-server

by io.github.cyanheads
OverviewDiscussionsAdmin

Get ORCID Researcher Works

orcid_get_works
Read-onlyIdempotent

Retrieve works associated with an ORCID iD — publications, datasets, software, preprints, and more. Returns work summaries with put-codes, titles, types, publication dates, journal names, and all external identifiers (DOIs, PMIDs, arXiv IDs, ISBNs). Narrow the list with work_types and year_from/year_to; the filters run over the whole record before paging, so matchedCount counts every match and workCount the whole record. The first 25 matching works are returned by default; page with offset and the returned nextOffset, or raise limit. Set include_external_ids to false to omit identifier lists for a lighter payload. Pass the putCode from each work to orcid_get_work_detail to retrieve the full record including abstract and contributors. External IDs are ready for chaining to Crossref, PubMed, or arXiv servers. Works come from the researcher or from member organizations such as Crossref or a university system; each work lists its sources and whether the researcher asserted it (selfAsserted). A researcher may not have linked all their publications.

Input Schema

NameRequiredDescriptionDefault
limitNoWorks per page. Default 25; a larger value returns at most 1,000 and says so.
offsetNoZero-based index of the first matching work to return (default 0). Continue with nextOffset.
year_toNoKeep only works published in or before this year; not before year_from.
orcid_idYesORCID iD — bare (0000-0001-2345-6789) or as an orcid.org URI (https://orcid.org/0000-0001-2345-6789). The check digit may be X or x.
year_fromNoKeep only works published in or after this year, read from the first four digits of publicationDate. Under either year bound, works with no publication date are left out and counted in the notice.
work_typesNoKeep only works of these types, matched against each workType (e.g. ["journal-article", "preprint"]; ORCID spells datasets data-set). Any listed type matches; an empty list keeps every type.
include_external_idsNoWhen true (default), each work carries its external identifiers (DOIs, PMIDs, arXiv IDs, ISBNs). Set false to omit them for a lighter payload when only titles, types, and dates are needed.

Output Schema

NameRequiredDescriptionDefault
errorNoPresent when the call failed. Absent on success.
worksNoMatching works in ORCID order, sliced to the requested offset and limit.
noticeNoDeprecated-iD disclosure naming the primary iD, requested/effective limit disclosure, the count of undated works a year filter left out, no-match or past-end guidance, or empty-record guidance: works may be private or not yet added.
offsetNoZero-based offset into the matching works applied for this response.
orcidIdNoNormalized ORCID iD (bare format).
orcidUriNoFull ORCID URI.
truncatedNoTrue when more matching works follow this page — fetch them with nextOffset.
workCountNoTotal works on this ORCID record, before filters, offset, and limit.
nextOffsetNoOffset to pass on the next call, with the same filters, to continue paging. Omitted when this response includes the last matching work.
matchedCountNoWorks matching work_types and the year range, before offset and limit; equals workCount when no filter is set.
returnedCountNoNumber of works returned in this response.
appliedFiltersNoThe filters applied before paging, present only when one is set.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed18 schema fields changed
    • changedInput schema / properties / limit / default
      Previous value: -50New value: +25
    • changedInput schema / properties / limit / description
      Previous value: -"Requested works (default 50, accepted maximum 10,000, effective maximum 1,000). Page locally with offset and nextOffset; the 64,000-byte response budget may return fewer."New value: +"Works per page. Default 25; a larger value returns at most 1,000 and says so."
    • changedInput schema / properties / offset / description
      Previous value: -"Zero-based index of the first work to return (default 0). Combine with limit to page through the full works list."New value: +"Zero-based index of the first matching work to return (default 0). Continue with nextOffset."
    • addedInput schema / properties / work_types
      Added value: +{
+  "description": "Keep only works of these types, matched against each workType (e.g. [\"journal-article\", \"preprint\"]; ORCID spells datasets data-set). Any listed type matches; an empty list keeps every type.",
+  "items": {
+    "description": "A work type in ORCID's vocabulary.",
+    "enum": [
+      "annotation",
+      "artistic-performance",
+      "blog-post",
+      "book-chapter",
+      "book-review",
+      "book",
+      "cartographic-material",
+      "clinical-study",
+      "conference-abstract",
+      "conference-output",
+      "conference-paper",
+      "conference-poster",
+      "conference-presentation",
+      "conference-proceedings",
+      "data-management-plan",
+      "data-set",
+      "design",
+      "dictionary-entry",
+      "disclosure",
+      "dissertation-thesis",
+      "edited-book",
+      "encyclopedia-entry",
+      "image",
+      "invention",
+      "journal-article",
+      "journal-issue",
+      "learning-object",
+      "lecture-speech",
+      "license",
+      "magazine-article",
+      "manual",
+      "moving-image",
+      "musical-composition",
+      "newsletter-article",
+      "newspaper-article",
+      "online-resource",
+      "other",
+      "patent",
+      "physical-object",
+      "preprint",
+      "registered-copyright",
+      "report",
+      "research-technique",
+      "research-tool",
+      "review",
+      "software",
+      "sound",
+      "spin-off-company",
+      "standards-and-policy",
+      "supervised-student-publication",
+      "technical-standard",
+      "test",
+      "trademark",
+      "transcription",
+      "translation",
+      "website",
+      "working-paper",
+      "undefined"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / year_from
      Added value: +{
+  "description": "Keep only works published in or after this year, read from the first four digits of publicationDate. Under either year bound, works with no publication date are left out and counted in the notice.",
+  "maximum": 9007199254740991,
+  "minimum": -9007199254740991,
+  "type": "integer"
+}
    • addedInput schema / properties / year_to
      Added value: +{
+  "description": "Keep only works published in or before this year; not before year_from.",
+  "maximum": 9007199254740991,
+  "minimum": -9007199254740991,
+  "type": "integer"
+}
    • changedOutput schema / anyOf
      Previous value: -[
-  {
-    "not": {
-      "required": [
-        "error"
-      ]
-    },
-    "required": [
-      "orcidId",
-      "orcidUri",
-      "workCount",
-      "returnedCount",
-      "offset",
-      "truncated",
-      "works"
-    ]
-  },
-  {
-    "required": [
-      "error"
-    ]
-  }
-]New value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "orcidId",
+      "orcidUri",
+      "workCount",
+      "matchedCount",
+      "returnedCount",
+      "offset",
+      "truncated",
+      "works"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]
    • addedOutput schema / properties / appliedFilters
      Added value: +{
+  "additionalProperties": false,
+  "description": "The filters applied before paging, present only when one is set.",
+  "properties": {
+    "workTypes": {
+      "description": "Work types kept (work_types).",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "yearFrom": {
+      "description": "Earliest publication year kept (year_from).",
+      "type": "number"
+    },
+    "yearTo": {
+      "description": "Latest publication year kept (year_to).",
+      "type": "number"
+    }
+  },
+  "type": "object"
+}
    • addedOutput schema / properties / matchedCount
      Added value: +{
+  "description": "Works matching work_types and the year range, before offset and limit; equals workCount when no filter is set.",
+  "type": "number"
+}
    • changedOutput schema / properties / nextOffset / description
      Previous value: -"Offset to pass on the next call to continue paging. Omitted when this response includes the final work."New value: +"Offset to pass on the next call, with the same filters, to continue paging. Omitted when this response includes the last matching work."
    • changedOutput schema / properties / notice / description
      Previous value: -"Requested/effective limit disclosure or empty-list guidance: works may be private or not yet added."New value: +"Deprecated-iD disclosure naming the primary iD, requested/effective limit disclosure, the count of undated works a year filter left out, no-match or past-end guidance, or empty-record guidance: works may be private or not yet added."
    • changedOutput schema / properties / offset / description
      Previous value: -"Zero-based offset applied to the full works list for this response."New value: +"Zero-based offset into the matching works applied for this response."
    • changedOutput schema / properties / returnedCount / description
      Previous value: -"Number of works returned in this response, after applying offset, limit, and the 64,000-byte response budget."New value: +"Number of works returned in this response."
    • changedOutput schema / properties / truncated / description
      Previous value: -"True when more works are available beyond this response, whether limit or the response budget ended the page — fetch them with nextOffset."New value: +"True when more matching works follow this page — fetch them with nextOffset."
    • changedOutput schema / properties / workCount / description
      Previous value: -"Total works available for this ORCID iD, before offset and limit are applied."New value: +"Total works on this ORCID record, before filters, offset, and limit."
    • changedOutput schema / properties / works / description
      Previous value: -"Works for this ORCID iD, sliced to the requested offset and limit and to the response budget."New value: +"Matching works in ORCID order, sliced to the requested offset and limit."
    • changedOutput schema / properties / works / items / properties / sources / items / properties / selfAsserted / description
      Previous value: -"True when the asserting party (the assertion origin when recorded, otherwise the source) is the requested ORCID iD; false when a member organization or another ORCID user asserted the item."New value: +"True when the asserting party (the assertion origin when recorded, otherwise the source) is the record's ORCID iD (orcidId); false when a member organization or another ORCID user asserted the item."
    • changedOutput schema / properties / works / items / properties / workType / description
      Previous value: -"Work type (e.g. journal-article, dataset, software, preprint)."New value: +"Work type in ORCID's vocabulary (e.g. journal-article, data-set, software, preprint), taken from the preferred version."
  2. Changed3 schema fields changed
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum works to return in this response (default 50, max 1000). The full list is sliced locally — page prolific records with offset and the returned nextOffset. A page stops early at the 64,000-byte response budget, so a large limit may return fewer works."New value: +"Requested works (default 50, accepted maximum 10,000, effective maximum 1,000). Page locally with offset and nextOffset; the 64,000-byte response budget may return fewer."
    • changedInput schema / properties / limit / maximum
      Previous value: -1000New value: +10000
    • changedOutput schema / properties / notice / description
      Previous value: -"Note when the works list is empty — neither the researcher nor a member organization may have added works, or they may be private."New value: +"Requested/effective limit disclosure or empty-list guidance: works may be private or not yet added."
  3. Changed7 schema fields changed
    • changedInput schema / properties / orcid_id / description
      Previous value: -"ORCID iD — bare format (0000-0001-2345-6789) or full URI (https://orcid.org/0000-0001-2345-6789)."New value: +"ORCID iD — bare (0000-0001-2345-6789) or as an orcid.org URI (https://orcid.org/0000-0001-2345-6789). The check digit may be X or x."
    • changedInput schema / properties / orcid_id / pattern
      Previous value: -"^(https?:\\/\\/orcid\\.org\\/)?\\d{4}-\\d{4}-\\d{4}-\\d{3}[\\dX]$"New value: +"^(?:(?:https?:\\/\\/)?(?:www\\.)?orcid\\.org\\/)?\\d{4}-\\d{4}-\\d{4}-\\d{3}[\\dXx]\\/?$"
    • changedOutput schema / properties / notice / description
      Previous value: -"Note when the works list is empty — may indicate no self-reported works or private visibility settings."New value: +"Note when the works list is empty — neither the researcher nor a member organization may have added works, or they may be private."
    • changedOutput schema / properties / works / items / description
      Previous value: -"Work summary record."New value: +"Work summary record — one ORCID work group, built from its preferred version."
    • changedOutput schema / properties / works / items / properties / externalIds / description
      Previous value: -"External identifiers (DOIs, PMIDs, arXiv IDs, ISBNs, etc.). Omitted when include_external_ids is false."New value: +"External identifiers of the whole ORCID work group (DOIs, PMIDs, arXiv IDs, ISBNs, etc.): the preferred version's own, part-of IDs such as an ISSN included, then each identifier only another source in the group holds. Omitted when include_external_ids is false."
    • addedOutput schema / properties / works / items / properties / sources
      Added value: +{
+  "description": "Every party that added this work to the ORCID record, one entry per distinct source in the work group, the preferred version's first. Empty when ORCID records no source.",
+  "items": {
+    "additionalProperties": false,
+    "description": "A party that asserted this item on the ORCID record.",
+    "properties": {
+      "assertionOriginName": {
+        "description": "Party the source added the item on behalf of, when ORCID records one — usually the researcher, for an item added through a search-and-link tool.",
+        "type": "string"
+      },
+      "name": {
+        "description": "Name of the person or member organization system that added the item (e.g. a university research information system, Crossref, Scopus - Elsevier). Absent when ORCID records no name.",
+        "type": "string"
+      },
+      "selfAsserted": {
+        "description": "True when the asserting party (the assertion origin when recorded, otherwise the source) is the requested ORCID iD; false when a member organization or another ORCID user asserted the item.",
+        "type": "boolean"
+      }
+    },
+    "required": [
+      "selfAsserted"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
    • addedOutput schema / properties / works / items / required
      Added value: +[
+  "sources"
+]
  4. Changed4 schema fields changed
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum works to return in this response (default 50, max 1000). The full list is sliced locally — page prolific records with offset and the returned nextOffset."New value: +"Maximum works to return in this response (default 50, max 1000). The full list is sliced locally — page prolific records with offset and the returned nextOffset. A page stops early at the 64,000-byte response budget, so a large limit may return fewer works."
    • changedOutput schema / properties / returnedCount / description
      Previous value: -"Number of works returned in this response, after applying offset and limit."New value: +"Number of works returned in this response, after applying offset, limit, and the 64,000-byte response budget."
    • changedOutput schema / properties / truncated / description
      Previous value: -"True when more works are available beyond this response — fetch them with nextOffset."New value: +"True when more works are available beyond this response, whether limit or the response budget ended the page — fetch them with nextOffset."
    • changedOutput schema / properties / works / description
      Previous value: -"Works for this ORCID iD, sliced to the requested offset and limit."New value: +"Works for this ORCID iD, sliced to the requested offset and limit and to the response budget."
  5. Changed6 schema fields changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedInput schema / additionalProperties
      Added value: +false
    • changedOutput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedOutput schema / anyOf
      Added value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "orcidId",
+      "orcidUri",
+      "workCount",
+      "returnedCount",
+      "offset",
+      "truncated",
+      "works"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]
    • addedOutput schema / properties / error
      Added value: +{
+  "additionalProperties": {},
+  "description": "Present when the call failed. Absent on success.",
+  "properties": {
+    "code": {
+      "description": "JSON-RPC error code for this failure.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "data": {
+      "additionalProperties": {},
+      "properties": {
+        "reason": {
+          "description": "Machine-readable failure mode. Declared by this tool: `profile_not_found`: The ORCID iD does not correspond to a registered researcher. Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "profile_not_found"
+          ],
+          "type": "string"
+        },
+        "recovery": {
+          "additionalProperties": {},
+          "description": "Actionable next step for the caller.",
+          "properties": {
+            "hint": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "hint"
+          ],
+          "type": "object"
+        },
+        "retryable": {
+          "description": "Whether retrying may succeed.",
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "message": {
+      "description": "Human-readable description of what went wrong.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code",
+    "message"
+  ],
+  "type": "object"
+}
    • removedOutput schema / required
      Removed value: -[
-  "orcidId",
-  "orcidUri",
-  "workCount",
-  "returnedCount",
-  "offset",
-  "truncated",
-  "works"
-]
  6. Changed12 schema fields changed
    • addedInput schema / properties / include_external_ids
      Added value: +{
+  "default": true,
+  "description": "When true (default), each work carries its external identifiers (DOIs, PMIDs, arXiv IDs, ISBNs). Set false to omit them for a lighter payload when only titles, types, and dates are needed.",
+  "type": "boolean"
+}
    • addedInput schema / properties / limit
      Added value: +{
+  "default": 50,
+  "description": "Maximum works to return in this response (default 50, max 1000). The full list is sliced locally — page prolific records with offset and the returned nextOffset.",
+  "maximum": 1000,
+  "minimum": 1,
+  "type": "integer"
+}
    • addedInput schema / properties / offset
      Added value: +{
+  "default": 0,
+  "description": "Zero-based index of the first work to return (default 0). Combine with limit to page through the full works list.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}
    • addedOutput schema / properties / nextOffset
      Added value: +{
+  "description": "Offset to pass on the next call to continue paging. Omitted when this response includes the final work.",
+  "type": "number"
+}
    • addedOutput schema / properties / offset
      Added value: +{
+  "description": "Zero-based offset applied to the full works list for this response.",
+  "type": "number"
+}
    • addedOutput schema / properties / returnedCount
      Added value: +{
+  "description": "Number of works returned in this response, after applying offset and limit.",
+  "type": "number"
+}
    • addedOutput schema / properties / truncated
      Added value: +{
+  "description": "True when more works are available beyond this response — fetch them with nextOffset.",
+  "type": "boolean"
+}
    • changedOutput schema / properties / workCount / description
      Previous value: -"Total number of works returned."New value: +"Total works available for this ORCID iD, before offset and limit are applied."
    • changedOutput schema / properties / works / description
      Previous value: -"Works associated with this ORCID iD."New value: +"Works for this ORCID iD, sliced to the requested offset and limit."
    • changedOutput schema / properties / works / items / properties / externalIds / description
      Previous value: -"External identifiers (DOIs, PMIDs, arXiv IDs, ISBNs, etc.)."New value: +"External identifiers (DOIs, PMIDs, arXiv IDs, ISBNs, etc.). Omitted when include_external_ids is false."
    • removedOutput schema / properties / works / items / required
      Removed value: -[
-  "externalIds"
-]
    • changedOutput schema / required
      Previous value: -[
-  "orcidId",
-  "orcidUri",
-  "workCount",
-  "works"
-]New value: +[
+  "orcidId",
+  "orcidUri",
+  "workCount",
+  "returnedCount",
+  "offset",
+  "truncated",
+  "works"
+]
  7. Changed1 schema field changed
    • addedOutput schema / properties / works / items / properties / putCode
      Added value: +{
+  "description": "Work put-code — pass to orcid_get_work_detail to fetch the full record including abstract and contributors.",
+  "type": "number"
+}
  8. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the readOnly/idempotent/openWorld annotations: it discloses that filtering happens over the whole record before paging, that default page size is 25, that offset/nextOffset drives paging, that limit has a practical ceiling, and that provenance includes source organization and selfAsserted flags. The caveat that a researcher may not have linked all publications is a real behavioral limitation an agent should know before concluding 'no more works exist'.

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 purpose, then filtering, paging, payload, and chaining in a logical order; nearly every clause carries operational value. Slightly dense — the return-field enumeration and the sources/selfAsserted sentence overlap with what the output schema already conveys.

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?

For a 7-parameter, open-world read tool with an output schema, the description covers everything an agent needs to call it correctly: filtering, paging, payload control, chaining to sibling tools and external services, and the incomplete-coverage caveat. Nothing material is left to inference.

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 baseline is 3, but the description adds genuine semantics the schema does not: that filters are applied before pagination (so matchedCount is the full match set, not the page), and that include_external_ids is a payload-weight tradeoff. Minor duplication of the year-filter null-date exclusion, which the schema already states.

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?

States a specific verb and resource ('Retrieve works associated with an ORCID iD') and immediately enumerates the resource scope (publications, datasets, software, preprints). It also distinguishes itself from the sibling orcid_get_work_detail by naming the putCode hand-off, so an agent can tell the two apart without opening either schema.

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?

Explicitly says how to narrow results (work_types, year_from/year_to) and when to disable include_external_ids ('for a lighter payload when only titles, types, and dates are needed'). It also names the alternative path — pass putCode to orcid_get_work_detail for abstracts and contributors — which is exactly the when-to-use-which signal an agent needs.

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

All orcid-mcp-server toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources