Semantic Scholar API: Get paper details
Finds a paper on Semantic Scholar by title, DOI or Semantic Scholar link and returns its abstract, one-sentence summary, authors, publication details, citation counts and a free PDF link when there is one.
Unofficial. Not affiliated with or endorsed by Semantic Scholar.
Inputs
Values from the run on Oct 31, 2026, shown under Output.
- Paper, required
paper Paper title, DOI, or Semantic Scholar paper link; for example, BERT: Pre-training of Deep Bidirectional Transformers.
https://www.semanticscholar.org/paper/204e3073870fae3d05bcbc2f6a8e263d9b72e776
Input as JSON
{ "paper": "https://www.semanticscholar.org/paper/204e3073870fae3d05bcbc2f6a8e263d9b72e776" }Output
{ "doi": null, "tldr": "A new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely is proposed, which generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.", "year": 2017, "title": "Attention is All you Need", "venue": "Neural Information Processing Systems", "authors": [ "Ashish Vaswani", "Noam Shazeer", "Niki Parmar" ], "abstract": "The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer…", "paper_link": "https://www.semanticscholar.org/paper/204e3073870fae3d05bcbc2f6a8e263d9b72e776" , "free_pdf_link": "https://arxiv.org/pdf/1706.03762.pdf" , "citation_count": 194179, "fields_of_study": [ "Computer Science" ], "reference_count": 41, "publication_date": "2017-06-12", "semantic_scholar_paper_id": "204e3073870fae3d05bcbc2f6a8e263d9b72e776", "influential_citation_count": 20803}Code
curl https://api.fous.com/v1/runs \ -H "Authorization: Bearer $FOUS_API_KEY" \ -H "Content-Type: application/json" \ -d '{"method":"semanticscholar.org/get_paper","input":{"paper":"https://www.semanticscholar.org/paper/204e3073870fae3d05bcbc2f6a8e263d9b72e776"}}' # Save as fous.py, then run: python3 fous.pyimport json, os, timefrom urllib.error import HTTPErrorfrom urllib.request import Request, urlopenAPI = "https://api.fous.com/v1/runs" KEY = os.environ["FOUS_API_KEY"]HEADERS = { "Authorization": f"Bearer {KEY}", "Content-Type": "application/json" ,}def call(url, body=None): data = json.dumps(body).encode() if body else None request = Request(url, data, HEADERS) try: with urlopen(request, timeout=120) as r: return r.status, json.load(r) except HTTPError as error: message = json.load(error)["error"]["message"] raise RuntimeError(message) from errorstatus, run = call(API, { "method": "semanticscholar.org/get_paper" , "input": { "paper": "https://www.semanticscholar.org/paper/204e3073870fae3d05bcbc2f6a8e263d9b72e776" }})# 202: still going after 30 s. Ask again until it ends.while status == 202: time.sleep(2) status, run = call(f"{API}/{run['id']}")print(json.dumps(run["data"], indent=2))// Save as fous.mjs, then run: node fous.mjsconst api = "https://api.fous.com/v1/runs" ;const headers = { Authorization: `Bearer ${process.env.FOUS_API_KEY}`, "Content-Type": "application/json" ,};let response = await fetch(api, { method: "POST", headers, body: JSON.stringify({ "method": "semanticscholar.org/get_paper" , "input": { "paper": "https://www.semanticscholar.org/paper/204e3073870fae3d05bcbc2f6a8e263d9b72e776" } }), signal: AbortSignal.timeout(120_000),});let run = await response.json();// 202: still going after 30 s. Ask again until it ends.while (response.status === 202) { await new Promise((done) => setTimeout(done, 2_000)); response = await fetch(`${api}/${run.id}`, { headers }); run = await response.json();}if (!response.ok) throw new Error(run.error.message);console.log(run.data);# Connect your agent to Fous once, over MCP (Streamable HTTP):# https://api.fous.com/mcp# Set FOUS_API_KEY first: create a key at https://app.fous.com/keys.# Claude Codeclaude mcp add \ --scope user \ --transport http fous https://api.fous.com/mcp \ --header "Authorization: Bearer ${FOUS_API_KEY:?Set FOUS_API_KEY to your Fous API key}"# Codexcodex mcp add fous \ --url https://api.fous.com/mcp \ --bearer-token-env-var FOUS_API_KEY# Cursor, VS Code, Windsurf, Cline and morenpx -y add-mcp https://api.fous.com/mcp -g -n fous \ --header "Authorization: Bearer ${FOUS_API_KEY:?Set FOUS_API_KEY to your Fous API key}"# Then ask your agent:# "Use Fous to run semanticscholar.org/get_paper# with {"paper":"https://www.semanticscholar.org/paper/204e3073870fae3d05bcbc2f6a8e263d9b72e776"}"Over HTTP, the answer’s data holds the output. A run still going after 30 seconds answers 202 with its id: ask GET /v1/runs/{id} until it ends.
Schema
Input schema
{ "type": "object", "required": [ "paper" ], "properties": { "paper": { "type": "string", "minLength": 1, "description": "Paper title, DOI, or Semantic Scholar paper link; for example, BERT: Pre-training of Deep Bidirectional Transformers." } }}Output schema
{ "type": "object", "required": [ "title", "abstract", "tldr", "authors", "year", "publication_date", "venue", "fields_of_study", "citation_count", "influential_citation_count", "reference_count", "free_pdf_link", "doi", "paper_link", "semantic_scholar_paper_id" ], "properties": { "doi": { "type": [ "string", "null" ], "description": "Digital object identifier." }, "tldr": { "type": [ "string", "null" ], "description": "One-sentence paper summary." }, "year": { "type": [ "integer", "null" ], "description": "Publication year." }, "title": { "type": "string", "description": "Paper title." }, "venue": { "type": [ "string", "null" ], "description": "Publication venue." }, "authors": { "type": "array", "items": { "type": "string" }, "description": "Author names." }, "abstract": { "type": [ "string", "null" ], "description": "Paper abstract." }, "paper_link": { "type": "string", "description": "Semantic Scholar paper page." }, "free_pdf_link": { "type": [ "string", "null" ], "description": "Link to a free PDF, if available." }, "citation_count": { "type": [ "integer", "null" ], "description": "Number of citations." }, "fields_of_study": { "type": "array", "items": { "type": "string" }, "description": "Fields of study." }, "reference_count": { "type": [ "integer", "null" ], "description": "Number of references." }, "publication_date": { "type": [ "string", "null" ], "description": "Publication date (YYYY-MM-DD)." }, "semantic_scholar_paper_id": { "type": "string", "description": "Semantic Scholar paper ID.", "x-fous-developer": true }, "influential_citation_count": { "type": [ "integer", "null" ], "description": "Number of influential citations." } }, "additionalProperties": false}- Price
- 1 credit per completed run (1¢ with pay as you go); failed runs are free.
- Method
semanticscholar.org/get_paper- Returns
- title, abstract, TLDR, authors, year, publication date, venue, fields of study, citation counts, free PDF link, DOI, Semantic Scholar link
Use it from your agent
Give your agent this line. It reads SKILL.md, gets a Fous API key and connects the Fous MCP server. Its run then takes the method semanticscholar.org/get_paper with the inputs above.
Ask your agent
- Can you pull up the abstract and citation count for "Attention Is All You Need" on Semantic Scholar?
- I need the authors, venue and publication year for the paper with DOI 10.1038/s41586-021-03819-2
- Is there a free PDF of "Deep Residual Learning for Image Recognition"? Also give me a one-line summary of it.
- Look up this Semantic Scholar link and tell me what the paper is about and how many times it's been cited: https://www.semanticscholar.org/paper/204e3073870fae3d05bcbc2f6a8e263d9b72e776
- What fields of study and publication date are listed for "Language Models are Few-Shot Learners"? Get me its DOI too.
See more
All Semantic Scholar methodsSearches Semantic Scholar for research papers in relevance order, with field of study, year range and open-access filters, returning AI one-sentence summaries, citations and free PDF links when available.
semanticscholar.org/search_papersFinds a Semantic Scholar author by name (optionally limited to a listed institution), picks the best-cited matching profile and returns their impact metrics and up to 10 most-cited papers.
semanticscholar.org/get_authorGets an arXiv paper's title, authors, abstract, subjects, submission dates and publication details from its exact title, arXiv link or number.
arxiv.org/get_paperGets the full PubMed abstract and publication details for one article by title, PubMed link, or PubMed number (PMID). A title is searched in PubMed titles first and must closely match a found article. Some articles have no abstract or free full text.
pubmed.ncbi.nlm.nih.gov/get_articleFinds a legal free copy of a paper by title or DOI, with its best available link and other copies. If no free copy is indexed, the copy links are null.
unpaywall.org/get_free_versionSearches OpenAlex scholarly works by topic, with optional institution, publication-year and open-access filters, ranked by relevance, citations or newest date.
openalex.org/search_papersFinds arXiv preprints by topic or title words, with optional author, subject, submission date range and sorting. Returns up to 100 papers with abstracts, subjects, dates and links.
arxiv.org/search_papersGets one public patent or published application by number, title, or Google Patents link, with claims, citations, family and classifications.
patents.google.com/get_patent