Skip to main content
Glama
smaniches

Semantic Scholar MCP Server

by smaniches
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

semantic_scholar_search_papers

Read-onlyIdempotent

Search 200M+ academic papers by relevance. Refine results using boolean operators, year, field, publication type, open access, and citation filters.

Instructions

Search for academic papers.

Relevance-ranked keyword search over 200M+ papers; supports boolean
operators (AND, OR, NOT) and quoted phrases, plus year, field-of-study,
publication-type, open-access, and citation-count filters. Page with
offset/limit (max 100 per call). For sorted or very large result sets
use semantic_scholar_bulk_search; to search inside paper full text use
semantic_scholar_snippet_search; to resolve one known title use
semantic_scholar_match_paper. Returns Markdown by default,
response_format='json' for raw JSON.

Input Schema

TableJSON 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": "search_papersOutput",
-  "type": "object"
-}New value: +null
  2. Changed3 schema fields changedv1.2.12
    • changedInput schema / $defs / PaperSearchInput / properties / limit / description
      Previous value: -"Max results (1-100)"New value: +"Max results per page (1-100, default 10); use semantic_scholar_bulk_search for result sets beyond 1000"
    • changedInput schema / $defs / PaperSearchInput / properties / offset / description
      Previous value: -"Pagination offset"New value: +"Pagination offset: pass the previous offset + limit to fetch the next page (default 0)"
    • changedInput schema / $defs / PaperSearchInput / properties / query / description
      Previous value: -"Search query"New value: +"Search query, e.g. 'protein language models'. Supports AND, OR, NOT operators and quoted phrases: '\"graph neural network\" AND drug'"
  3. Changed2 schema fields changedv1.2.6
    • addedInput schema / $defs / PaperSearchInput / properties / api_key / deprecated
      Added value: +true
    • changedInput schema / $defs / PaperSearchInput / 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. Changed1 schema field changedv1.0.3
    • addedInput schema / $defs / PaperSearchInput / 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"
+}
  5. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, covering safety and side-effect expectations. The description builds on this by adding search-specific behavioral details: boolean operators, quoted phrases, filter types, pagination via offset/limit, and default vs. JSON response format. It does not cover potential rate limits or error behaviors, but these are not critical for a read-only search tool when annotations already signal safety.

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 a single dense paragraph that front-loads the core purpose, then packs capabilities, limitations, alternatives, and output format into just a few sentences. Every clause earns its place; there is no fluff or repetition of schema field names. The structure flows logically from what → how → when-to-use-other-tools → output format.

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 tool's complexity (multiple filters, pagination, output formats) and the absence of an output schema, the description fully equips an agent to select and invoke it correctly. It covers input essentials, pagination behavior, alternative tools for edge cases, and return format. The schema and annotations cover parameter details and safety, so no critical gaps remain.

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?

The input schema already contains detailed descriptions for every parameter (e.g., year formats, limit bounds, query examples). The tool description adds meaningful context that is not fully in the schema: relevance ranking semantics, the availability of specific filter families, and that response_format='json' yields raw JSON. Although the description does not enumerate each parameter by name, the schema provides that, and the description enhances understanding of when and how to use them.

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 opens with a specific verb+resource ('Search for academic papers') and immediately clarifies the scope: relevance-ranked keyword search over 200M+ papers. It distinguishes itself from sibling tools by explicitly naming alternatives (bulk_search, snippet_search, match_paper) and explaining when each is appropriate, leaving no ambiguity about its purpose.

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?

The description provides explicit when-to-use guidance by stating that for sorted or very large result sets one should use semantic_scholar_bulk_search, for full-text search one should use semantic_scholar_snippet_search, and for resolving a single known title one should use semantic_scholar_match_paper. It also notes pagination limits (max 100 per call), which is key for correct invocation.

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