Science

Data source: Semantic Scholar API

MCP Endpoint (Streamable HTTP) https://context.gnist.ai/mcp/semantic-scholar/

Authentication

All requests require a Gnist-API-Key header (or api_key query parameter).

Free tier: 100 calls/day. Get your API key.

Tools (8)

search_papers
get_paper
get_citations
get_references
search_authors
get_author
recommend_papers
report_feedback

search_papers

Search 200M+ academic papers in Semantic Scholar.

Find papers across all scientific disciplines. Returns titles, authors,
citation counts, venues, and links to open-access PDFs when available.
Use paper IDs from results with get_paper, get_citations, get_references,
and recommend_papers.

Args:
query: Search keywords or phrase.
limit: Number of results (1-100, default 10).
offset: Pagination offset for paging through results.
year: Year or year range filter.
fields_of_study: Filter by academic field(s).

Returns:
Papers with paperId, title, year, venue, authors, citationCount, doi.

Parameter	Type	Required	Description
`query`	`string`	required	Search query for academic papers (e.g. "transformer attention mechanism", "CRISPR gene editing", "climate change mitigation").
`limit`	`integer`	optional	Number of results to return (1-100, default 10). (default: 10)
`offset`	`integer`	optional	Pagination offset for additional results (default 0). (default: 0)
`year`	`any`	optional	Year filter — single year ("2023"), range ("2020-2023"), or open range ("2020-").
`fields_of_study`	`any`	optional	Filter by academic field (e.g. ["Computer Science"], ["Medicine", "Biology"]).

JSON-RPC Request

{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "id": 1,
  "params": {
    "name": "search_papers",
    "arguments": {
      "query": "example"
    }
  }
}

get_paper

Get detailed information about a specific academic paper.

Retrieve full paper details including abstract, citation/reference counts,
authors, fields of study, and AI-generated TLDR summary. Accepts multiple
ID formats: Semantic Scholar paper ID, DOI, ArXiv ID, PMID, or CorpusId.

Args:
paper_id: Paper identifier in any supported format.

Returns:
Full paper details with abstract, authors, citations, TLDR, and links.

Parameter	Type	Required	Description
`paper_id`	`string`	required	Paper identifier — S2 ID (40-char hex), DOI (e.g. "10.1038/s41586-021-03819-2"), ArXiv ID (e.g. "2301.12345"), or prefixed ID (e.g. "PMID:12345", "CorpusId:12345").

JSON-RPC Request

{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "id": 1,
  "params": {
    "name": "get_paper",
    "arguments": {
      "paper_id": "example"
    }
  }
}

get_citations

Get papers that cite a given paper.

Explore a paper's citation graph by finding all papers that reference it.
Useful for tracking research impact, finding follow-up work, and
discovering how a paper has influenced subsequent research.

Args:
paper_id: Paper identifier in any supported format.
limit: Number of citing papers to return (1-100, default 20).
offset: Pagination offset.

Returns:
List of citing papers with title, year, venue, authors, citationCount.

Parameter	Type	Required	Description
`paper_id`	`string`	required	Paper identifier (S2 ID, DOI, ArXiv ID, or prefixed ID).
`limit`	`integer`	optional	Number of citing papers to return (1-100, default 20). (default: 20)
`offset`	`integer`	optional	Pagination offset (default 0). (default: 0)

JSON-RPC Request

{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "id": 1,
  "params": {
    "name": "get_citations",
    "arguments": {
      "paper_id": "example"
    }
  }
}

get_references

Get papers referenced by a given paper.

Explore a paper's bibliography — the works it cites. Useful for
understanding a paper's foundations, finding seminal works in a field,
and building reading lists from authoritative sources.

Args:
paper_id: Paper identifier in any supported format.
limit: Number of referenced papers to return (1-100, default 20).
offset: Pagination offset.

Returns:
List of referenced papers with title, year, venue, authors, citationCount.

Parameter	Type	Required	Description
`paper_id`	`string`	required	Paper identifier (S2 ID, DOI, ArXiv ID, or prefixed ID).
`limit`	`integer`	optional	Number of referenced papers to return (1-100, default 20). (default: 20)
`offset`	`integer`	optional	Pagination offset (default 0). (default: 0)

JSON-RPC Request

{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "id": 1,
  "params": {
    "name": "get_references",
    "arguments": {
      "paper_id": "example"
    }
  }
}

search_authors

Search for academic authors by name.

Find researchers by name and see their publication counts, citation counts,
h-index, and institutional affiliations. Use authorId from results with
get_author for detailed profiles.

Args:
query: Author name to search for.
limit: Number of results (1-100, default 10).

Returns:
Authors with authorId, name, paperCount, citationCount, hIndex, affiliations.

Parameter	Type	Required	Description
`query`	`string`	required	Author name to search for (e.g. "Yann LeCun", "Geoffrey Hinton").
`limit`	`integer`	optional	Number of results to return (1-100, default 10). (default: 10)

JSON-RPC Request

{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "id": 1,
  "params": {
    "name": "search_authors",
    "arguments": {
      "query": "example"
    }
  }
}

get_author

Get an author's profile by Semantic Scholar author ID.

Retrieve detailed author information including paper count, citation count,
h-index, and affiliations.

Args:
author_id: Numeric S2 author ID from search_authors results.

Returns:
Author profile with name, paperCount, citationCount, hIndex, affiliations.

Parameter	Type	Required	Description
`author_id`	`string`	required	Semantic Scholar author ID (numeric, e.g. "1688882").

JSON-RPC Request

{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "id": 1,
  "params": {
    "name": "get_author",
    "arguments": {
      "author_id": "example"
    }
  }
}

recommend_papers

Get paper recommendations based on a seed paper.

Uses Semantic Scholar's recommendation engine to find related papers
you might want to read next. Useful for literature review, discovering
adjacent research, and expanding knowledge in a topic area.

Args:
paper_id: Paper to get recommendations for.
limit: Number of recommendations (1-100, default 10).

Returns:
Recommended papers similar to the seed paper.

Parameter	Type	Required	Description
`paper_id`	`string`	required	Paper identifier (S2 ID, DOI, ArXiv ID, or prefixed ID) to get recommendations for.
`limit`	`integer`	optional	Number of recommendations (1-100, default 10). (default: 10)

JSON-RPC Request

{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "id": 1,
  "params": {
    "name": "recommend_papers",
    "arguments": {
      "paper_id": "example"
    }
  }
}

report_feedback

Report a bug, feature request, or general feedback for this data source.

Use this when something doesn't work as expected, when you'd like
a new feature, or when you have suggestions for improvement.

Args:
feedback: Describe the issue or suggestion.
feedback_type: One of 'bug', 'feature_request', or 'general'.

Parameter	Type	Required	Description
`feedback`	`string`	required
`feedback_type`	`string`	optional	(default: "general")

JSON-RPC Request

{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "id": 1,
  "params": {
    "name": "report_feedback",
    "arguments": {
      "feedback": "example"
    }
  }
}

Quick Start

Shell

curl -X POST "https://context.gnist.ai/mcp/semantic-scholar/" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "Gnist-API-Key: YOUR_API_KEY" \
  -d '{"jsonrpc": "2.0", "method": "tools/call", "id": 1, "params": {"name": "search_papers", "arguments": {"query": "example"}}}'

Python

import httpx

resp = httpx.post(
    "https://context.gnist.ai/mcp/semantic-scholar/",
    headers={"Gnist-API-Key": "YOUR_API_KEY", "Content-Type": "application/json"},
    json={
  "jsonrpc": "2.0",
  "method": "tools/call",
  "id": 1,
  "params": {
    "name": "search_papers",
    "arguments": {
      "query": "example"
    }
  }
},
)
print(resp.json())