Semanticscholar

Get Paper

get_paper

Read-onlyIdempotent

Get full metadata for a single paper by ID. Accepts a Semantic Scholar paper ID, or a prefixed ID like "DOI:10.1145/3292500", "arXiv:2106.15928", or "CorpusId:215416146". Returns abstract, TLDR summary, authors, venue, citation/reference counts, fields of study, and open-access PDF. Keyless.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`paper_id`	Yes	Paper identifier. A Semantic Scholar ID, or prefixed: "DOI:10...", "arXiv:2106.15928", "CorpusId:...".

Output Schema

TableJSON Schema

Name	Required	Description
`doi`	No	Digital Object Identifier
`url`	No	URL to the paper
`tldr`	No	TL;DR summary of the paper
`year`	No	Publication year
`title`	No	Paper title
`venue`	No	Publication venue
`authors`	No	Paper authors
`journal`	No	Journal name
`abstract`	No	Paper abstract
`paper_id`	No	Semantic Scholar paper ID
`citation_count`	No	Number of citations
`is_open_access`	No	Whether the paper is open access
`fields_of_study`	No	Fields of study tags
`open_access_pdf`	No	URL to open access PDF if available
`reference_count`	No	Number of references in the paper
`publication_date`	No	Full publication date
`publication_types`	No	Publication type tags
`influential_citations`	No	Number of influential citations

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed2 schema fields changedJun 20, 2026

addedInput schema / examples

Added value: +[
+  {
+    "paper_id": "DOI:10.1038/s41586-021-03819-2"
+  },
+  {
+    "paper_id": "ArXiv:2312.10997"
+  }
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "abstract": {
+      "description": "Paper abstract",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "authors": {
+      "description": "Paper authors",
+      "items": {
+        "properties": {
+          "id": {
+            "description": "Author ID",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "name": {
+            "description": "Author name",
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "citation_count": {
+      "description": "Number of citations",
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "doi": {
+      "description": "Digital Object Identifier",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "fields_of_study": {
+      "description": "Fields of study tags",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "influential_citations": {
+      "description": "Number of influential citations",
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "is_open_access": {
+      "description": "Whether the paper is open access",
+      "type": [
+        "boolean",
+        "null"
+      ]
+    },
+    "journal": {
+      "description": "Journal name",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "open_access_pdf": {
+      "description": "URL to open access PDF if available",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "paper_id": {
+      "description": "Semantic Scholar paper ID",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "publication_date": {
+      "description": "Full publication date",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "publication_types": {
+      "description": "Publication type tags",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "reference_count": {
+      "description": "Number of references in the paper",
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "title": {
+      "description": "Paper title",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "tldr": {
+      "description": "TL;DR summary of the paper",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "url": {
+      "description": "URL to the paper",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "venue": {
+      "description": "Publication venue",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "year": {
+      "description": "Publication year",
+      "type": [
+        "number",
+        "null"
+      ]
+    }
+  },
+  "type": "object"
+}

First observedJun 10, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, confirming it is a safe read operation. The description adds value by specifying return fields (abstract, TLDR, authors, etc.) and noting 'Keyless' (no API key required), which enhances transparency beyond annotations.

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

Conciseness5/5

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

The description is only three sentences, each carrying important information: purpose, ID formats, and return fields. No unnecessary words. Highly efficient.

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?

Given the single parameter, annotations covering safety, and an implied output schema, the description is complete. It covers what the tool does, how to specify the paper, and what to expect in return. No gaps for an agent.

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%, and the schema provides a good description of the parameter. The description reinforces this with examples of valid ID prefixes (DOI, arXiv, CorpusId), adding clarity. However, it largely overlaps with the schema, so the added value is modest.

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?

The description clearly states the verb 'Get full metadata' for a 'single paper by ID', distinguishing it from sibling tools like 'search_papers' and 'get_paper_citations'. It also provides examples of valid ID prefixes, making the purpose unambiguous.

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?

The description explains when to use this tool (to get metadata for a single paper by ID) and gives valid ID formats. It does not explicitly mention alternatives or when not to use it, but the context from sibling tool names and common sense fills the gap. Slight lack of explicit exclusion.

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

All Semanticscholar tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0

Disambiguation4/5

Most tools have clearly distinct purposes, especially the core ones like get_paper, search_papers, and entity_profile. However, some pairs like ask_pipeworx and ask_pipeworx_grounded, or the polymarket tools, could cause momentary confusion, though descriptions help differentiate.

Naming Consistency2/5

Naming patterns are inconsistent: tools use verb_noun (e.g., get_paper), noun_phrase (e.g., polymarket_arbitrage), and bare verbs (e.g., forget, recall). There is no unifying pattern, and styles like 'pipeworx_feedback' vs 'search_papers' further add to the inconsistency.

Tool Count3/5

With 34 tools, the set covers a broad range of domains (academic papers, company data, prediction markets, memory, subscriptions). While the scope justifies the number, it feels slightly heavy and could benefit from consolidation or clearer grouping.

Completeness4/5

The tool set covers major functionalities for research, data retrieval, and monitoring, with only minor gaps (e.g., limited to US public companies, npm-only dependency scanning). Overall, the surface is comprehensive for the stated capabilities.

Get Paper

Input Schema

Output Schema

Schema Changelog

TDQS

Glama MCP Gateway

TDQS

Resources