scopus-mcp

Overview Schema Source Related Servers Discussions Admin

scopus_get_abstract

Read-onlyIdempotent

Retrieve full paper details from Scopus using a Scopus ID, DOI, EID, or PubMed ID to access abstracts, authors, keywords, and citation data.

Instructions

Retrieve full paper details from Scopus using any supported identifier.

Identifier types:

scopus_id — Scopus internal numeric ID (e.g. "85123456789")
doi — Digital Object Identifier (e.g. "10.1016/j.labeco.2024.102505")
eid — Electronic ID (e.g. "2-s2.0-85123456789")
pubmed_id — PubMed/MEDLINE numeric ID

Returns: title, full abstract, authors with affiliations, keywords, subject areas, citation count, DOI, and open access status.

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": {
      "identifier_type": "<identifier_type>",
      "identifier": "<identifier>"
    },
    "name": "scopus_get_abstract"
  }
}

Input Schema

Name	Required	Description	Default
`identifier`	Yes	The identifier value (strip any 'SCOPUS_ID:' prefix from scopus_id)
`identifier_type`	Yes	Type of identifier being provided

Output Schema

Name	Required	Default
`doi`	No
`title`	No
`source`	No	scopus
`authors`	No
`abstract`	No
`keywords`	No
`scopus_id`	No
`served_at`	No
`cover_date`	No
`access_note`	No
`open_access`	No
`publication`	No
`retrieved_at`	No
`subject_areas`	No
`cited_by_count`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 6, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$defs": {
+    "PaperAuthor": {
+      "additionalProperties": true,
+      "properties": {
+        "affiliation": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null,
+          "title": "Affiliation"
+        },
+        "name": {
+          "title": "Name",
+          "type": "string"
+        },
+        "retrieved_at": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null,
+          "title": "Retrieved At"
+        },
+        "scopus_author_id": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null,
+          "title": "Scopus Author Id"
+        },
+        "served_at": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null,
+          "title": "Served At"
+        },
+        "source": {
+          "default": "scopus",
+          "title": "Source",
+          "type": "string"
+        }
+      },
+      "required": [
+        "name"
+      ],
+      "title": "PaperAuthor",
+      "type": "object"
+    }
+  },
+  "additionalProperties": true,
+  "properties": {
+    "abstract": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Abstract"
+    },
+    "access_note": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Access Note"
+    },
+    "authors": {
+      "items": {
+        "$ref": "#/$defs/PaperAuthor"
+      },
+      "title": "Authors",
+      "type": "array"
+    },
+    "cited_by_count": {
+      "anyOf": [
+        {
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Cited By Count"
+    },
+    "cover_date": {
+      "default": "",
+      "title": "Cover Date",
+      "type": "string"
+    },
+    "doi": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Doi"
+    },
+    "keywords": {
+      "items": {
+        "type": "string"
+      },
+      "title": "Keywords",
+      "type": "array"
+    },
+    "open_access": {
+      "anyOf": [
+        {
+          "type": "boolean"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Open Access"
+    },
+    "publication": {
+      "default": "",
+      "title": "Publication",
+      "type": "string"
+    },
+    "retrieved_at": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Retrieved At"
+    },
+    "scopus_id": {
+      "default": "",
+      "title": "Scopus Id",
+      "type": "string"
+    },
+    "served_at": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Served At"
+    },
+    "source": {
+      "default": "scopus",
+      "title": "Source",
+      "type": "string"
+    },
+    "subject_areas": {
+      "items": {
+        "type": "string"
+      },
+      "title": "Subject Areas",
+      "type": "array"
+    },
+    "title": {
+      "default": "",
+      "title": "Title",
+      "type": "string"
+    }
+  },
+  "title": "AbstractResult",
+  "type": "object"
+}

First observedv0.1.0Jun 23, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive, openWorld behavior, so the safety profile is covered. The description adds the payload contents (title, abstract, authors, keywords, citation count, DOI, OA status), but says nothing about failure modes, entitlement/API-key requirements, or rate limits for a tool that depends on an external subscription service.

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 purpose sentence followed by a scannable identifier-type list and a single compact returns line. The returns line duplicates what the output schema already carries, so it is slightly redundant rather than wasteful.

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?

With an output schema, full annotation coverage, and only two required parameters, the description provides everything needed to construct a correct call. The only missing piece is guidance on selecting this tool over its bulk sibling and what happens when an identifier does not resolve.

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 3 is the floor, and the description earns an extra point by giving a concrete example value for each identifier_type, which the enum-only schema does not. It also complements the schema's note about stripping the 'SCOPUS_ID:' prefix from scopus_id.

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 concrete verb and resource (retrieve paper details from Scopus) and makes the single-record-by-identifier scope explicit through the identifier enumeration. It does not name the closest sibling, scopus_get_abstracts (bulk), so the singular/plural distinction is left to the agent to infer from the names.

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

Usage Guidelines3/5

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

Usage is implied by the identifier-type list — an agent can see this is the tool for fetching one paper when it already holds an ID. There is no explicit when-to-use versus scopus_get_abstracts or scopus_search, and no stated prerequisites such as 'requires a resolved identifier' or fallback behavior on lookup failure.

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

Deploy Server