# Semantic Scholar API

> Semantic Scholar returns research papers, paper details, citations, and author metrics as a workflow and API.

Semantic Scholar (S2) Search papers finds relevant studies by topic or title words, with optional field, year, and access filters. Get paper returns a paper’s abstract, summary, publication details, and citation influence from its title, DOI, or Semantic Scholar link. Get author returns impact metrics and up to 10 most-cited papers from a researcher name, with an optional institution to match listed affiliations.

- Page: https://fous.com/tools/semantic-scholar
- Handle: `@semantic-scholar`
- Category: [Science](https://fous.com/tools/category/science)
- Source website: https://semanticscholar.org
- Last verified: Sep 29, 2026

## Methods

### Get author

Operation `get_author`, version 1. 1 credit per completed call. Failed calls without a completed billing receipt are free; completed work can remain charged if delivery is interrupted.

Get a Semantic Scholar author’s impact metrics and up to 10 most-cited papers from their name. When an institution is provided, only listed affiliations can be matched; authors without a listed affiliation cannot match.

**Input**

| Field | Type | Required | Example | Description |
|---|---|---|---|---|
| `author` | string | yes | `"Yoshua Bengio"` | Researcher name, for example Fei-Fei Li. |
| `institution` | string | no | `"Southwest Petroleum University"` | Institution to match against listed affiliations, for example Southwest Petroleum University. |

**Input schema**

```json
{
  "type": "object",
  "required": [
    "author"
  ],
  "properties": {
    "author": {
      "type": "string",
      "minLength": 1,
      "description": "Researcher name, for example Fei-Fei Li.",
      "examples": [
        "Yoshua Bengio",
        "Fei-Fei Li",
        "Fei Li"
      ]
    },
    "institution": {
      "type": "string",
      "minLength": 1,
      "description": "Institution to match against listed affiliations, for example Southwest Petroleum University.",
      "examples": [
        "Southwest Petroleum University"
      ]
    }
  },
  "additionalProperties": false,
  "examples": [
    {
      "author": "Yoshua Bengio"
    },
    {
      "author": "Fei-Fei Li"
    },
    {
      "author": "Fei Li",
      "institution": "Southwest Petroleum University"
    }
  ]
}
```

**Output**

| Field | Type | Example | Description |
|---|---|---|---|
| `name` | string | `"Yoshua Bengio"` | Researcher name shown on Semantic Scholar. |
| `h_index` | integer | `212` | Author h-index. |
| `homepage` | string or null | `"https://scholar.google.com/citations?user=rDfyQnIAAAAJ&hl=en"` | Researcher homepage, if listed. |
| `author_id` | string | `"1751762"` | Semantic Scholar author ID. |
| `top_papers` | array |  | Up to 10 most-cited publications, from highest to lowest citation count. |
| `top_papers[].year` | integer or null | `1998` |  |
| `top_papers[].title` | string | `"Gradient-based learning applied to document recognition"` |  |
| `top_papers[].venue` | string or null | `"Proceedings of the IEEE"` |  |
| `top_papers[].citations` | integer | `62855` |  |
| `top_papers[].paper_link` | string | `"https://www.semanticscholar.org/paper/162d958ff885f1462aeda91cd72582323fd6a1f4"` |  |
| `affiliations` | array |  | Listed institutions, or an empty list when none are listed. |
| `total_citations` | integer | `574497` | Total Semantic Scholar citations. |
| `author_page_link` | string | `"https://www.semanticscholar.org/author/1751762"` | Researcher page on Semantic Scholar. |
| `number_of_papers` | integer | `811` | Number of papers attributed to this author. |

**Example input**

```json
{
  "author": "Yoshua Bengio"
}
```

**Example output**

```json
{
  "name": "Yoshua Bengio",
  "h_index": 212,
  "homepage": null,
  "author_id": "1751762",
  "top_papers": [
    {
      "year": 1998,
      "title": "Gradient-based learning applied to document recognition",
      "venue": "Proceedings of the IEEE",
      "citations": 62855,
      "paper_link": "https://www.semanticscholar.org/paper/162d958ff885f1462aeda91cd72582323fd6a1f4"
    },
    {
      "year": 2015,
      "title": "Deep Learning",
      "venue": null,
      "citations": 38310,
      "paper_link": "https://www.semanticscholar.org/paper/2913c2bf3f92b5ae369400a42b2d27cc5bc05ecb"
    },
    {
      "year": 2014,
      "title": "Neural Machine Translation by Jointly Learning to Align and Translate",
      "venue": "International Conference on Learning Representations",
      "citations": 30076,
      "paper_link": "https://www.semanticscholar.org/paper/fa72afa9b2cbc8f0d7b05d52548906610ffbb9c5"
    }
  ],
  "affiliations": [],
  "total_citations": 574497,
  "author_page_link": "https://www.semanticscholar.org/author/1751762",
  "number_of_papers": 811
}
```

### Get paper

Operation `get_paper`, version 1. 1 credit per completed call. Failed calls without a completed billing receipt are free; completed work can remain charged if delivery is interrupted.

Get a paper’s abstract, short summary, authors, publication details, and citation influence from its title, DOI, or Semantic Scholar link. Some papers lack a publication date, summary, or free PDF.

**Input**

| Field | Type | Required | Example | Description |
|---|---|---|---|---|
| `paper` | string | yes | `"https://www.semanticscholar.org/paper/204e3073870fae3d05bcbc2f6a8e263d9b72e776"` | Paper title, DOI, or Semantic Scholar paper link; for example, BERT: Pre-training of Deep Bidirectional Transformers. |

**Input schema**

```json
{
  "type": "object",
  "required": [
    "paper"
  ],
  "properties": {
    "paper": {
      "type": "string",
      "description": "Paper title, DOI, or Semantic Scholar paper link; for example, BERT: Pre-training of Deep Bidirectional Transformers.",
      "examples": [
        "https://www.semanticscholar.org/paper/204e3073870fae3d05bcbc2f6a8e263d9b72e776",
        "BERT: Pre-training of Deep Bidirectional Transformers",
        "10.18653/v1/N19-1423"
      ]
    }
  },
  "additionalProperties": false,
  "examples": [
    {
      "paper": "https://www.semanticscholar.org/paper/204e3073870fae3d05bcbc2f6a8e263d9b72e776"
    },
    {
      "paper": "BERT: Pre-training of Deep Bidirectional Transformers"
    },
    {
      "paper": "10.18653/v1/N19-1423"
    }
  ]
}
```

**Output**

| Field | Type | Example | Description |
|---|---|---|---|
| `doi` | string or null | `"10.18653/v1/N19-1423"` | Digital object identifier. |
| `tldr` | string or null | `"A new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence an` | One-sentence paper summary. |
| `year` | integer or null | `2017` | Publication year. |
| `title` | string | `"Attention is All you Need"` | Paper title. |
| `venue` | string or null | `"Neural Information Processing Systems"` | Publication venue. |
| `authors` | array |  | Author names. |
| `abstract` | string or null |  | Paper abstract. |
| `paper_link` | string | `"https://www.semanticscholar.org/paper/204e3073870fae3d05bcbc2f6a8e263d9b72e776"` | Semantic Scholar paper page. |
| `free_pdf_link` | string or null | `"https://arxiv.org/pdf/1706.03762.pdf"` | Link to a free PDF, if available. |
| `citation_count` | integer or null | `194179` | Number of citations. |
| `fields_of_study` | array |  | Fields of study. |
| `reference_count` | integer or null | `41` | Number of references. |
| `publication_date` | string or null | `"2017-06-12"` | Publication date (YYYY-MM-DD). |
| `semantic_scholar_paper_id` | string | `"204e3073870fae3d05bcbc2f6a8e263d9b72e776"` | Semantic Scholar paper ID. |
| `influential_citation_count` | integer or null | `20803` | Number of influential citations. |

**Example input**

```json
{
  "paper": "https://www.semanticscholar.org/paper/204e3073870fae3d05bcbc2f6a8e263d9b72e776"
}
```

**Example output**

```json
{
  "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 app…",
  "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 d…",
  "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
}
```

### Search papers

Operation `search_papers`, version 1. 1 credit per completed call. Failed calls without a completed billing receipt are free; completed work can remain charged if delivery is interrupted.

Search Semantic Scholar for research papers in relevance order, with available AI one-sentence summaries, citations, and free PDF links. Summaries and direct PDF links may be unavailable for some papers.

**Input**

| Field | Type | Required | Example | Description |
|---|---|---|---|---|
| `field` | string | no | `"Computer Science"` | Field of study in plain words, for example Medicine or Computer Science. |
| `query` | string | yes | `"long covid fatigue"` | Topic or words from a paper title, for example long covid fatigue. |
| `end_year` | integer | no | `2024` | Latest publication year, for example 2025. |
| `start_year` | integer | no | `2021` | Earliest publication year, for example 2020. |
| `max_results` | integer | no | `12` | Maximum papers to return, for example 10 (up to 100). |
| `open_access_only` | boolean | no | `true` | Only show open-access papers, for example true. |

**Input schema**

```json
{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "field": {
      "type": "string",
      "description": "Field of study in plain words, for example Medicine or Computer Science.",
      "examples": [
        "Computer Science"
      ]
    },
    "query": {
      "type": "string",
      "minLength": 1,
      "description": "Topic or words from a paper title, for example long covid fatigue.",
      "examples": [
        "long covid fatigue",
        "qzxvunlikelypaperword987654321",
        "graph neural networks"
      ]
    },
    "end_year": {
      "type": "integer",
      "maximum": 2100,
      "minimum": 1800,
      "description": "Latest publication year, for example 2025.",
      "examples": [
        2024
      ]
    },
    "start_year": {
      "type": "integer",
      "maximum": 2100,
      "minimum": 1800,
      "description": "Earliest publication year, for example 2020.",
      "examples": [
        2021
      ]
    },
    "max_results": {
      "type": "integer",
      "default": 10,
      "maximum": 100,
      "minimum": 1,
      "description": "Maximum papers to return, for example 10 (up to 100).",
      "x-fous-developer": true,
      "examples": [
        12
      ]
    },
    "open_access_only": {
      "type": "boolean",
      "default": false,
      "description": "Only show open-access papers, for example true.",
      "examples": [
        true
      ]
    }
  },
  "additionalProperties": false,
  "examples": [
    {
      "query": "long covid fatigue"
    },
    {
      "query": "qzxvunlikelypaperword987654321"
    },
    {
      "field": "Computer Science",
      "query": "graph neural networks",
      "end_year": 2024,
      "start_year": 2021,
      "max_results": 12,
      "open_access_only": true
    }
  ]
}
```

**Output**

| Field | Type | Example | Description |
|---|---|---|---|
| `papers` | array |  |  |
| `papers[].year` | integer or null | `2025` |  |
| `papers[].title` | string | `"Feasibility and acceptance of transdermal auricular vagus nerve stimulation using a TENS device in females suffering fr` |  |
| `papers[].venue` | string or null | `"Wiener Klinische Wochenschrift"` |  |
| `papers[].authors` | array |  |  |
| `papers[].summary` | string or null | `"The treatment was found to be safe, with no significant side effects reported; however, further research with larger st` |  |
| `papers[].paper_id` | string | `"5c9424cb6b209327d75e17424b75613f0863777a"` |  |
| `papers[].paper_link` | string | `"https://www.semanticscholar.org/paper/5c9424cb6b209327d75e17424b75613f0863777a"` |  |
| `papers[].free_pdf_link` | string or null | `"https://link.springer.com/content/pdf/10.1007/s00508-025-02501-1.pdf"` |  |
| `papers[].number_of_citations` | integer or null | `11` |  |

**Example input**

```json
{
  "query": "long covid fatigue"
}
```

**Example output**

```json
{
  "papers": [
    {
      "year": 2025,
      "title": "Feasibility and acceptance of transdermal auricular vagus nerve stimulation using a TENS device in females suffering from long COVID fatigue",
      "venue": "Wiener Klinische Wochenschrift",
      "authors": [
        "Veronika Pfoser‐Poschacher",
        "M. Keilani"
      ],
      "summary": "The treatment was found to be safe, with no significant side effects reported; however, further research with larger study groups is needed to confirm these findings and examine the long-term effects …",
      "paper_id": "5c9424cb6b209327d75e17424b75613f0863777a",
      "paper_link": "https://www.semanticscholar.org/paper/5c9424cb6b209327d75e17424b75613f0863777a",
      "free_pdf_link": "https://link.springer.com/content/pdf/10.1007/s00508-025-02501-1.pdf",
      "number_of_citations": 11
    },
    {
      "year": 2024,
      "title": "Efficacy of dual-task augmented reality rehabilitation in non-hospitalized adults with self-reported long COVID fatigue and cognitive impairment: a pilot study",
      "venue": "Neurological Sciences",
      "authors": [
        "M. Deodato",
        "Caterina Qualizza"
      ],
      "summary": "The preliminary results from this study suggest that dual-task rehabilitation could be a feasible protocol to support cognitive symptoms recovery after COVID-19 and could be helpful in those individua…",
      "paper_id": "ae2e60355e15a7131b2e1bdafc2f139b7049ce0e",
      "paper_link": "https://www.semanticscholar.org/paper/ae2e60355e15a7131b2e1bdafc2f139b7049ce0e",
      "free_pdf_link": null,
      "number_of_citations": 17
    }
  ]
}
```

## Quick start

Replace `YOUR_API_KEY` with a Fous API key. To create one, open Developers at the bottom of Fous Studio, turn on Developer mode, then go to API keys (https://app.fous.com/keys). Change the values in `input` to run the same tool on new data.

```bash
curl 'https://api.fous.com/v1/query' \
  --fail-with-body --silent --show-error --max-time 180 \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H 'Content-Type: application/json' \
  --data-raw '{
  "api": "@semantic-scholar",
  "visibility": "public",
  "operation": "get_author",
  "version": 1,
  "input": {
    "author": "Yoshua Bengio"
  },
  "response": {
    "format": "json"
  }
}'
```

```python
# Save as fous.py and run with python3 fous.py. No packages needed.
import json
import urllib.error
import urllib.request

api_key = "YOUR_API_KEY"

body = json.loads("{\n  \"api\": \"@semantic-scholar\",\n  \"visibility\": \"public\",\n  \"operation\": \"get_author\",\n  \"version\": 1,\n  \"input\": {\n    \"author\": \"Yoshua Bengio\"\n  },\n  \"response\": {\n    \"format\": \"json\"\n  }\n}")
request = urllib.request.Request(
    "https://api.fous.com/v1/query",
    data=json.dumps(body).encode("utf-8"),
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    method="POST",
)
try:
    with urllib.request.urlopen(request, timeout=180) as response:
        result = json.load(response)
except urllib.error.HTTPError as error:
    raise RuntimeError(f"HTTP {error.code}: {error.read().decode('utf-8', errors='replace')}") from error
if result.get("success") is False:
    raise RuntimeError(result.get("error", {}).get("message", "Request failed"))
print(json.dumps(result["data"]["output"], indent=2))
```

```typescript
// Save as fous.mts and run with npx tsx fous.mts.
const apiKey = "YOUR_API_KEY";

const response = await fetch("https://api.fous.com/v1/query", {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  signal: AbortSignal.timeout(180_000),
  body: JSON.stringify({
  "api": "@semantic-scholar",
  "visibility": "public",
  "operation": "get_author",
  "version": 1,
  "input": {
    "author": "Yoshua Bengio"
  },
  "response": {
    "format": "json"
  }
}),
});
type ApiResult = { success: boolean; data?: { output: unknown }; error?: { message: string } };
const result: ApiResult = await response.json();
if (!response.ok || result.success === false) {
  throw new Error(result.error?.message ?? `HTTP ${response.status}`);
}
if (!result.data) throw new Error("Missing API response data");
console.log(result.data.output);
```

## Use from an AI assistant

Connect this tool to Claude Code, Claude Desktop, Cursor, VS Code, Codex and any MCP client as its own MCP server. Each method is a typed tool whose arguments are the method’s input.

- Server URL: `https://api.fous.com/mcp/tools/semantic-scholar`
- Authorization: `Authorization: Bearer <Fous API key>`

**Tools**

- `get_author`: Get author. 1 credit per completed call. Failed calls without a completed billing receipt are free; completed work can remain charged if delivery is interrupted.
- `get_paper`: Get paper. 1 credit per completed call. Failed calls without a completed billing receipt are free; completed work can remain charged if delivery is interrupted.
- `search_papers`: Search papers. 1 credit per completed call. Failed calls without a completed billing receipt are free; completed work can remain charged if delivery is interrupted.
- `fous_get_run`: the result of a run that was still going, by its `request_id`. Free.

Claude Code:

```bash
claude mcp add --scope user --transport http fous-semantic-scholar https://api.fous.com/mcp/tools/semantic-scholar --header "Authorization: Bearer ${FOUS_API_KEY:?Set FOUS_API_KEY to your Fous API key}"
```

To give the assistant every tool, connect `https://api.fous.com/mcp`: it finds one with `fous_search_tools` and runs it with `fous_run_tool`. Setup for other clients: https://fous.com/llms-full.txt.

## Use cases

- Find papers on a research topic within a publication-year range.
- Review paper abstracts, authors, venues, and citation counts.
- Identify open-access papers with available free PDF links.
- Compare researchers using citation totals and h-index.
- Compile researchers’ most-cited publications for literature reviews.

## FAQ

### Can I run it with my own inputs?

Yes. Change the inputs in Studio and press Run, or send new inputs from your code, or ask a connected AI assistant.

### Can I call this Semantic Scholar tool as an API?

Yes. Send a POST request to /v1/query with your Fous API key and the inputs, and get JSON back.

### How much does it cost?

Each completed run costs 1 credit. Failed runs without a completed receipt are free; completed work can remain charged if delivery is interrupted. With pay as you go, a credit costs 1¢. Monthly plans cost less per credit.

### Do I need a Semantic Scholar account?

No. You only need a Fous account.

### How current is the data?

Fous gets the data from semanticscholar.org when you run it. Some results are reused for up to 24 hours, and results that use your account or key are never reused. It was last verified on Sep 29, 2026.

### Which papers cover a topic I’m researching?

Search papers returns relevant papers for a topic or title words, with optional field, year, and open-access filters.

### What are a paper’s abstract and citation count?

Get paper returns a paper’s abstract, citation count, and other publication details from its title, DOI, or Semantic Scholar link.

### What are a researcher’s impact metrics?

Get author returns a researcher’s h-index, total citations, paper count, and up to 10 most-cited papers.

## Related

- [Google Scholar API](https://fous.com/tools/google-scholar.md): Google Scholar provides papers, citing papers, ready-made citations and researcher profiles with metrics and up to 20 top-cited papers; public access may be temporarily limited.
- [OpenAlex API](https://fous.com/tools/openalex.md): OpenAlex is an open catalog of scholarly research and connections, offering ranked papers and institution research summaries with annual output, leading topics, and coauthors.
- [arXiv API](https://fous.com/tools/arxiv.md): arXiv returns up to 100 matching research preprints or individual paper details, and newly announced subject papers in announcement order; announcement dates may differ from today, and replacements are excluded.
- [PubMed API](https://fous.com/tools/pubmed.md): PubMed searches medical and life-science articles by topic and retrieves one article’s abstract and publication details; abstracts and free full-text links may be unavailable.
- [Unpaywall API](https://fous.com/tools/unpaywall.md): Find free-to-read scholarly papers and their legal copies.
- [ORCID API](https://fous.com/tools/orcid.md): Researcher identifiers and public research records.
- [Crossref API](https://fous.com/tools/crossref.md): Find scholarly works and format citations from their registered metadata.
- [bioRxiv API](https://fous.com/tools/biorxiv.md): Biology and medicine preprints from bioRxiv and medRxiv.
- [All Science tools](https://fous.com/tools/category/science)