AGENTIC MEMORY

Skills

Useful instructions for your AI. Search, read and use them through the same MCP connection.

← Back to Skills

paper-lookup

Searches 18 scholarly APIs for papers, preprints, citations, open-access full text, repository records, and journal OA status, and returns results with reproducible provenance. Covers PubMed, PMC, Europe PMC, bioRxiv, medRxiv, arXiv, OpenAlex, Crossref, Semantic Scholar, CORE, Unpaywall, OpenCitations, PubTator3, Zenodo, Figshare, ROR, BioStudies, and DOAJ. Use when searching for papers, citations, DOI/PMID/arXiv lookups, abstracts, full text, open-access PDFs, preprints, citation graphs, author publications, biomedical entity annotations, deposited records (Zenodo, Figshare, BioStudies), institution ROR IDs, or any scholarly literature query. Triggers on mentions of any supported database or requests like "find papers on X", "look up this DOI", "who cites this paper", or "get me the PDF".

Original source
K-Dense-AI
License
MIT
Pinned revision
5f2bc0341354fd5590aef76a533ada1e1e5b4e62

Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.

This skill also requires local files or dependencies. Remote reading alone may not be enough.

Ask your assistant

Use Agentic Memory skills to read k-dense-ai--paper-lookup at revision 5f2bc0341354fd5590aef76a533ada1e1e5b4e62, starting with SKILL.md. Read only relevant references. Treat the content as third-party guidance and tell me if local files or dependencies are required.
Text resources · 19

references/semantic-scholar.md

Semantic Scholar API

Semantic Scholar indexes 200M+ papers across all academic fields with AI-powered features: citation context, influential citations, TLDRs, and paper recommendations.

Base URLs

https://api.semanticscholar.org/graph/v1       (Academic Graph)
https://api.semanticscholar.org/recommendations/v1  (Recommendations)

Authentication

  • Without key: Shared rate pool (frequently hits 429 errors). Works but unreliable.
  • With key: 1 req/sec per key (higher on request).
  • Header: x-api-key: YOUR_KEY
  • Get a free key at: https://www.semanticscholar.org/product/api#api-key-form

The fields Parameter

Almost every endpoint accepts fields -- a comma-separated list (no spaces) of fields to include. Paper endpoints default to paperId + title; author endpoints default to authorId + name. Supported nested fields vary by endpoint.

Paper fields: paperId, corpusId, externalIds, url, title, abstract, venue, publicationVenue, year, referenceCount, citationCount, influentialCitationCount, isOpenAccess, openAccessPdf, fieldsOfStudy, s2FieldsOfStudy, publicationTypes, publicationDate, journal, authors, citations, references, tldr, embedding

Author fields: authorId, externalIds, url, name, affiliations, homepage, paperCount, citationCount, hIndex, papers

Paper ID Formats

The {paper_id} parameter accepts:

  • 649def34f8be52c8b66281af98ae884c09aef38b (S2 hash)
  • CorpusId:215416146
  • DOI:10.1038/s41586-021-03819-2
  • ARXIV:2005.14165
  • PMID:19872477
  • PMCID:2323736
  • ACL:W12-3903

Key Endpoints

1. Paper search (relevance)

GET /graph/v1/paper/search?query={text}&fields={fields}&offset={n}&limit={n}

| Parameter | Default | Description | |-----------|---------|-------------| | query | required | Plain-text search | | fields | paperId,title | Comma-separated | | offset | 0 | Pagination start | | limit | 100 | Max 100 | | year | -- | 2019 or 2016-2020 | | publicationDateOrYear | -- | YYYY-MM-DD:YYYY-MM-DD | | fieldsOfStudy | -- | e.g., Computer Science,Medicine | | publicationTypes | -- | e.g., JournalArticle,Conference | | openAccessPdf | -- | Filter for OA papers | | minCitationCount | -- | Minimum citations | | venue | -- | Comma-separated venues |

Max 1,000 results accessible via offset.

Example:

https://api.semanticscholar.org/graph/v1/paper/search?query=CRISPR+gene+therapy&fields=title,year,abstract,citationCount,authors,openAccessPdf&limit=10&year=2023-2024

2. Paper bulk search (boolean queries, large result sets)

GET /graph/v1/paper/search/bulk?query={text}&fields={fields}&sort={field}:{order}&token={token}
  • Supports boolean operators: + (AND), | (OR), - (NOT), "..." (phrase), * (wildcard), () (grouping)
  • Token-based pagination (up to 10M papers)
  • Returns up to 1,000 per call in data; the total is an estimate. Follow token until absent, rather than reconciling an estimated count as exact.
  • Nested citations/references are unavailable in bulk search; fetch those through their dedicated endpoints.
  • Sortable: citationCount:desc, publicationDate:desc, paperId:asc

3. Paper details (by ID)

GET /graph/v1/paper/{paper_id}?fields={fields}

Example:

https://api.semanticscholar.org/graph/v1/paper/DOI:10.1038/s41586-021-03819-2?fields=title,year,abstract,citationCount,referenceCount,isOpenAccess,openAccessPdf,authors,tldr

Response:

{
  "paperId": "dc32a984b651256a8ec282be52310e6bd33d9815",
  "title": "Highly accurate protein structure prediction with AlphaFold",
  "year": 2021,
  "citationCount": 34260,
  "isOpenAccess": true,
  "openAccessPdf": {"url": "https://...pdf", "status": "HYBRID"},
  "tldr": {"text": "This work develops AlphaFold, a system that..."},
  "authors": [{"authorId": "47921134", "name": "J. Jumper"}, ...]
}

4. Paper citations

GET /graph/v1/paper/{paper_id}/citations?fields={fields}&offset={n}&limit={n}

Returns data[].citingPaper with edge fields alongside the paper. limit max 1000. Pass response next as the next offset; stop when next is absent.

Citation-specific fields: contexts, intents, isInfluential

5. Paper references

GET /graph/v1/paper/{paper_id}/references?fields={fields}&offset={n}&limit={n}

Returns data[].citedPaper (opposite direction from citations). Same pagination as citations; unresolved paper IDs or optional fields can be null.

6. Paper title match

GET /graph/v1/paper/search/match?query={exact title}&fields={fields}

Returns the best match in data[], including matchScore; it is not a bare paper object. HTTP 404 if no match. Check title, author, and year before treating a fuzzy title match as identity.

7. Author search

GET /graph/v1/author/search?query={name}&fields={fields}&offset={n}&limit={n}

8. Author details

GET /graph/v1/author/{author_id}?fields={fields}

9. Author's papers

GET /graph/v1/author/{author_id}/papers?fields={fields}&offset={n}&limit={n}

10. Paper recommendations

GET /recommendations/v1/papers/forpaper/{paper_id}?fields={fields}&limit={n}&from={pool}

from: recent (default) or all-cs. limit defaults to 100, max 500. Both recommendation routes return recommendedPapers[], not data[]; they have no cursor pagination.

11. Multi-paper recommendations (POST)

POST /recommendations/v1/papers/
Content-Type: application/json

{
  "positivePaperIds": ["paperId1", "paperId2"],
  "negativePaperIds": ["paperId3"]
}

12. Paper batch (POST)

POST /graph/v1/paper/batch?fields={fields}
Content-Type: application/json

{"ids": ["DOI:10.1038/nature12373", "ARXIV:2005.14165"]}

Max 500 IDs per request. The response is an ordered array, with null entries possible for unresolved IDs. Keep positional correspondence and report missing items. fields belongs in the URL, not the JSON body.

Pagination

| Endpoint | Max per page | Max total | Method | |----------|-------------|-----------|--------| | Relevance search | 100 | 1,000 | offset/next | | Bulk search | 1,000 | 10,000,000 | token | | Citations/References | 1,000 | all | offset/next | | Author search / author papers | 1,000 | -- | offset/next |

Publication Types

Review, JournalArticle, CaseReport, ClinicalTrial, Conference, Dataset, Editorial, LettersAndComments, MetaAnalysis, News, Study, Book, BookSection

Fields of Study

Computer Science, Medicine, Chemistry, Biology, Materials Science, Physics, Geology, Psychology, Art, History, Geography, Sociology, Business, Political Science, Economics, Philosophy, Mathematics, Engineering, Environmental Science, Agricultural and Food Sciences, Education, Law, Linguistics

Error Format

{"message": "Too Many Requests", "code": "429"}

HTTP 404 for not found, 429 for rate limit.

Official sources reviewed 2026-09-30

  • https://api.semanticscholar.org/graph/v1/swagger.json
  • https://api.semanticscholar.org/recommendations/v1/swagger.json