Skip to main content
Glama
Sign In
smaniches

Semantic Scholar MCP Server

by smaniches
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

semantic_scholar_recommendations

Read-onlyIdempotent

Get paper recommendations based on a seed paper.

Instructions

Get paper recommendations based on a seed paper.

Provide one paper you already know (e.g. paper_id='ARXIV:1706.03762') and
receive up to `limit` similar papers. from_pool picks the candidate pool:
'recent' (default, recently published papers from all fields) or 'all-cs'
(computer-science papers of any age). When steering with several positive
or negative examples, use semantic_scholar_multi_recommend instead. An
unknown seed ID raises a not-found error. Client-side requests use a
1.0-second unkeyed interval and a conservative 1.1-second authenticated
default; explicitly higher S2-assigned quotas can be configured. 429/502/503
responses retry automatically with backoff. Returns Markdown by default,
response_format='json' for raw JSON.

Input Schema

NameRequiredDescriptionDefault
paramsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.2.13
    • changedOutput schema / (root)
      Previous value: -{
-  "properties": {
-    "result": {
-      "title": "Result",
-      "type": "string"
-    }
-  },
-  "required": [
-    "result"
-  ],
-  "title": "get_recommendationsOutput",
-  "type": "object"
-}New value: +null
  2. Changed3 schema fields changedv1.2.12
    • changedInput schema / $defs / PaperRecommendationsInput / properties / from_pool / description
      Previous value: -"Paper pool: 'recent' (default) or 'all-cs'"New value: +"Candidate pool: 'recent' (default; recently published papers from all fields) or 'all-cs' (computer-science papers of any age)"
    • changedInput schema / $defs / PaperRecommendationsInput / properties / limit / description
      Previous value: -"Max recommendations"New value: +"Max recommendations (1-100, default 10)"
    • changedInput schema / $defs / PaperRecommendationsInput / properties / paper_id / description
      Previous value: -"Seed paper ID for recommendations"New value: +"Seed paper the recommendations should resemble: a 40-character S2 hex ID ('649def34f8be52c8b66281af98ae884c09aef38b'), 'DOI:10.18653/v1/N18-3011', 'ARXIV:1706.03762', 'PMID:19872477', 'CorpusId:215416146', 'ACL:W12-3903', or 'URL:https://...'"
  3. Changed2 schema fields changedv1.2.6
    • addedInput schema / $defs / PaperRecommendationsInput / properties / api_key / deprecated
      Added value: +true
    • changedInput schema / $defs / PaperRecommendationsInput / properties / api_key / description
      Previous value: -"API key (overrides SEMANTIC_SCHOLAR_API_KEY env var)"New value: +"API key (overrides SEMANTIC_SCHOLAR_API_KEY env var). Deprecated: prefer the environment variable. Removal planned for v2.0.0."
  4. Changed2 schema fields changedv1.0.3
    • addedInput schema / $defs / PaperRecommendationsInput / properties / api_key
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "API key (overrides SEMANTIC_SCHOLAR_API_KEY env var)",
+  "title": "Api Key"
+}
    • addedInput schema / $defs / PaperRecommendationsInput / properties / from_pool
      Added value: +{
+  "default": "recent",
+  "description": "Paper pool: 'recent' (default) or 'all-cs'",
+  "title": "From Pool",
+  "type": "string"
+}
  5. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Given the readOnlyHint and idempotentHint annotations, the description still adds significant new context: error handling (unknown seed raises not-found), rate limiting details (1.0-second unkeyed interval, 1.1-second authenticated default, configurable quotas), automatic retries on 429/502/503 with backoff, and return format defaults. This is exactly the kind of operational context annotations cannot convey.

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 front-loaded with the core purpose, then branches into options, alternatives, error behavior, and operational details. Every sentence adds concrete value; no fluff.

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 tool with no output schema, the description covers all critical aspects: what it returns (up to limit similar papers in Markdown or JSON), how to control scope (from_pool), when to use an alternative, error conditions, and rate-limit/retry behavior. Nothing essential for correct invocation is missing.

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 low (0% per context signals, though the schema itself does include some descriptions), so the description must carry the burden. It explains the purpose of paper_id, from_pool, response_format, and mentions limit. It doesn't fully describe the api_key parameter or the exact format for paper_id, but provides enough functional meaning.

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+resource ('Get paper recommendations based on a seed paper') and clarifies scope immediately. It also distinguishes itself from the sibling semantic_scholar_multi_recommend by explaining that multi_recommend should be used for steering with several examples.

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 tells the agent when to use this tool (one seed paper) vs the alternative (semantic_scholar_multi_recommend for multiple positive/negative examples). It also explains the effect of from_pool options, leaving little to inference.

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

Deploy Server

Other Tools