Skip to main content
Glama

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). The first 50 works are returned by default; workCount reports the total available, and prolific records are paged with offset and the returned nextOffset (or raise limit). A page also stops early once the response reaches its 64,000-byte budget, so returnedCount can come in below limit; truncated and nextOffset then carry the continuation. 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

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum 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.
offsetNoZero-based index of the first work to return (default 0). Combine with limit to page through the full works list.
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.
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

TableJSON Schema
NameRequiredDescriptionDefault
errorNoPresent when the call failed. Absent on success.
worksNoWorks for this ORCID iD, sliced to the requested offset and limit and to the response budget.
noticeNoNote when the works list is empty — neither the researcher nor a member organization may have added works, or they may be private.
offsetNoZero-based offset applied to the full works list for this response.
orcidIdNoNormalized ORCID iD (bare format).
orcidUriNoFull ORCID URI.
truncatedNoTrue when more works are available beyond this response, whether limit or the response budget ended the page — fetch them with nextOffset.
workCountNoTotal works available for this ORCID iD, before offset and limit are applied.
nextOffsetNoOffset to pass on the next call to continue paging. Omitted when this response includes the final work.
returnedCountNoNumber of works returned in this response, after applying offset, limit, and the 64,000-byte response budget.

Schema Changelog

Changes observed during successful MCP inspections.

  1. 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"
+]
  2. 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."
  3. 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"
-]
  4. 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"
+]
  5. 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"
+}
  6. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations cover the safety profile (readOnly, idempotent, openWorld), so the bar is lower, yet the description still discloses non-obvious behavior: the 64,000-byte page budget, early-stopping with truncated/nextOffset, selfAsserted provenance, multiple sources per work, and that records may be incomplete.

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 behavior, then pagination and chaining. It is dense with ~8 sentences but nearly all carry actionable information; slightly long, though nothing is clearly redundant.

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?

An output schema exists, so return-value detail is not required in the description, and the remaining gaps an agent needs (paging, optional fields, provenance, downstream chaining, sibling handoff) are all covered.

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 meaning beyond the schema: include_external_ids=false for a lighter payload, limit as a local slice vs page size, and the offset/nextOffset continuation pattern. It reinforces rather than merely repeats.

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?

Opens with a specific verb+resource ('Retrieve works associated with an ORCID iD') and enumerates the covered resource types (publications, datasets, software, preprints). It also distinguishes itself from orcid_get_work_detail by naming the sibling and the putCode handoff.

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 routes the agent: use this list tool first, then pass putCode to orcid_get_work_detail for abstract and contributors, and chain external IDs to Crossref/PubMed/arXiv. Pagination guidance (offset + nextOffset, or raise limit) tells the agent when this tool suffices vs when to page.

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