# Research Paper Search: arXiv, PubMed, Crossref + Full Text (`poised_beardlichen/research-paper-search`) Actor Use this when you need scholarly papers by topic, DOI, arXiv ID or PMID from arXiv, Crossref and Europe PMC/PubMed. $0.0015/paper, $0.01/legal open-access full text; empty searches free. Input: {"query":"10.1038/s41586-021-03819-2","includeFullText":true}. Output: metadata, licence, full text. - **URL**: https://apify.com/poised_beardlichen/research-paper-search.md - **Developed by:** [Isaac](https://apify.com/poised_beardlichen) (community) - **Categories:** AI, Developer tools - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing Pay per event This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event ## What's an Apify Actor? An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md. ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run. For examples already wired to this Actor's own input schema, see the [API](#api) section below. Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`). # README ## Research Paper Search API: arXiv, PubMed & Crossref with Open-Access Full Text **Use this when you or your AI agent need scholarly papers in clean JSON.** One call searches **arXiv**, **Crossref** (150M+ DOIs) and **Europe PMC** (every PubMed record, plus PubMed Central and preprints). Results are merged and de-duplicated, with title, authors, year, venue, DOI, arXiv ID, PMID/PMCID, abstract, citation count, open-access status, **licence** and PDF link. Switch on full text and you also get the paper as **Markdown**, but only from legal open-access copies under permissive licences. - 🔎 **Three free scholarly databases in one call.** Search by keywords, or look up a DOI, arXiv ID, PMID or PMC ID - 📄 **Legal full text.** Europe PMC open-access XML, CC BY arXiv papers and CC BY publisher PDFs, converted to clean Markdown for RAG and LLMs - ⚖️ **Copyright-safe by design.** Full text is only delivered for CC0, CC BY, CC BY-SA or public-domain papers. Everything else gets metadata, the licence and a link. No Google Scholar scraping, no shadow libraries - 💸 **Pay only for results.** $0.0015 per paper and $0.01 per full text actually delivered. Empty searches and unavailable full texts are free - 🤖 **Agent-ready.** One string input, compact JSON, typical calls finish in 1–5 seconds, and it works with the Apify MCP server and agentic payments ### What can I use it for? - **Literature reviews and research agents:** find the key papers on a topic, then read the open-access ones in full - **RAG pipelines:** feed permissively licensed full texts into your vector database with the licence attached - **Citation checking:** confirm that a DOI, title or arXiv ID exists and get correct metadata (stops LLM citation hallucinations) - **Biomedical research:** PubMed coverage with PMIDs, PMCIDs and open-access status ### Input | Field | What it does | |---|---| | `query` | Keywords, a DOI (`10.1038/s41586-021-03819-2`), an arXiv ID (`1706.03762`), `PMID:31452104` or `PMC8371605` | | `queries` | Optional batch of extra queries | | `maxResults` | Papers per query (default 10, max 100) | | `includeFullText` | Add legal open-access full text as Markdown | | `openAccessOnly`, `yearFrom`, `yearTo` | Filters | | `sources` | `arxiv`, `crossref`, `europepmc` (default: all three) | ```json { "query": "10.1038/s41586-021-03819-2", "includeFullText": true } ``` ### Output example ```json { "title": "Highly accurate protein structure prediction with AlphaFold", "authors": ["John Jumper", "Richard Evans", "..."], "year": 2021, "venue": "Nature", "doi": "10.1038/s41586-021-03819-2", "pmid": "34265844", "pmcid": "PMC8371605", "citedByCount": 46513, "isOpenAccess": true, "licence": "cc-by", "url": "https://doi.org/10.1038/s41586-021-03819-2", "sources": ["crossref", "europepmc"], "fullTextStatus": "delivered", "fullTextSource": "europepmc-xml", "fullText": "# Highly accurate protein structure prediction with AlphaFold\n\n## Abstract ..." } ``` `fullTextStatus` is one of `delivered`, `not_requested`, `licence_not_permissive` (open but e.g. CC BY-NC or the arXiv default licence, so you get a link only), `no_downloadable_copy`, `not_open_access` or `fetch_failed`. You are charged for full text only when it says `delivered`. ### Use it from the API or with AI agents ```bash curl -X POST "https://api.apify.com/v2/acts/poised_beardlichen~research-paper-search/run-sync-get-dataset-items?token=" \ -H "Content-Type: application/json" -d '{"query": "retrieval augmented generation evaluation", "maxResults": 5}' ``` ```python from apify_client import ApifyClient client = ApifyClient("") run = client.actor("poised_beardlichen/research-paper-search").call(run_input={"query": "1706.03762"}) print(list(client.dataset(run["defaultDatasetId"]).iterate_items())) ``` **MCP:** add `https://mcp.apify.com/?tools=poised_beardlichen/research-paper-search` to Claude, Cursor or any MCP client. AI agents can also pay per call through Apify agentic payments, with no Apify account needed. ### Pricing | Event | Price | |---|---| | Paper returned (metadata) | $0.0015 | | Open-access full text delivered | $0.01 | 10 papers cost $0.015. Searches with no results, and full texts that are unavailable or not permissively licensed, cost nothing. Set **Maximum cost per run** and the Actor stops cleanly at your limit. ### FAQ **Why don't I get full text for every open-access paper?** Many "free to read" papers do not allow redistribution (for example CC BY-NC, CC BY-ND or arXiv's default licence). For those we return the licence and a link to the publisher's or arXiv's own copy, so you can read it there. **Do you use Google Scholar or Sci-Hub?** No. Only the official, free APIs of arXiv, Crossref and Europe PMC. **Is PubMed included?** Yes. Europe PMC indexes every PubMed record and adds PubMed Central full texts and preprints. **How fresh is the data?** Each call queries the live APIs, so new papers appear as soon as the databases index them. **What about citation counts?** They come from Crossref and Europe PMC and can differ from Google Scholar. **How fast is it?** A keyword search of 10 papers usually takes 1–3 seconds. Full text adds about 1–2 seconds per paper (arXiv requests are paced to respect arXiv's rate limits). ### Other tools by us - [Audio & Video Transcriber (Whisper)](https://apify.com/poised_beardlichen/audio-video-transcriber): MP3, WAV, M4A and MP4 to text, timed segments and SRT subtitles at $0.006 per audio minute. - [Bulk Email Verifier](https://apify.com/poised_beardlichen/email-verifier-bulk): syntax, MX, disposable and role-address checks at $0.30 per 1,000 emails. - [Website Screenshot & PDF API](https://apify.com/poised_beardlichen/website-screenshot-pdf): bulk screenshots and PDFs of any page with cookie banners and pop-ups removed. - [Website Screenshot & PDF for AI Agents](https://apify.com/poised_beardlichen/website-screenshot-pdf-agent): fast single-page screenshots and PDFs for agents, from $0.0015 per screenshot. - [PDF to Text & Markdown with OCR](https://apify.com/poised_beardlichen/pdf-to-text-markdown-ocr): turn PDFs, DOCX and scans into clean, LLM-ready Markdown. - [Image to Text OCR API](https://apify.com/poised_beardlichen/image-to-text-ocr): extract text from PNG, JPEG, TIFF and WebP images in 27 languages. - [Bulk PageSpeed & Lighthouse Checker](https://apify.com/poised_beardlichen/pagespeed-lighthouse-checker): Lighthouse scores, Core Web Vitals and top fixes for many URLs. - [Website Tech Stack Detector](https://apify.com/poised_beardlichen/tech-stack-detector): CMS, ecommerce, analytics, CDN and 7,600+ other technologies behind any website. - [SEC EDGAR Financials & Filings](https://apify.com/poised_beardlichen/sec-edgar-financials): US company financials, filings and 10-K sections as compact JSON. - [Website Legitimacy & Scam Check](https://apify.com/poised_beardlichen/website-legitimacy-check): domain age, SSL, look-alike brands, VAT and LEI signals at $0.008 per site. - [Bulk Phone Number Validator](https://apify.com/poised_beardlichen/phone-number-validator): validity, E.164 format, line type and region for any number at $0.70 per 1,000. - [Company Contact & Profile Extractor](https://apify.com/poised_beardlichen/company-contact-extractor): generic emails, phones, socials and profile from any company website at $0.004 per site. - [UK & Australia Company Check](https://apify.com/poised_beardlichen/company-registry-check): ABN, ACN, ASIC and Companies House status and red flags from $0.003 per company. - [Company Careers & Open Jobs Lookup](https://apify.com/poised_beardlichen/careers-jobs-lookup): open jobs from Greenhouse, Lever, Ashby and more at $0.0015 per job. ### Support Found a wrong result or a missing licence? Open an issue on the **Issues** tab and we will fix it fast. ### More agent tools from Monie Tools - [Website Screenshot & PDF for AI Agents](https://apify.com/poised_beardlichen/website-screenshot-pdf-agent): Use this when an AI agent needs a clean screenshot or PDF of a web page (cookie banners, ads, chats removed). - [Website Tech Stack Detector — Wappalyzer Alternative](https://apify.com/poised_beardlichen/tech-stack-detector): to know what a website is built with: CMS, ecommerce platform, frameworks, analytics, ad pixels, CDN, hosting, payment and marketing tools, with versions. - [SEC EDGAR API: Financials, Filings & 10-K Sections](https://apify.com/poised_beardlichen/sec-edgar-financials): SEC data on a US public company: profile, standardised financials, filings, 10-K/10-Q sections or EDGAR full-text search. - [Website Legitimacy & Scam Check: Domain Age, SSL, VAT, LEI](https://apify.com/poised_beardlichen/website-legitimacy-check): must judge if a website or company looks legitimate before buying, partnering or clicking. # Actor input Schema ## `query` (type: `string`): Keywords (e.g. 'retrieval augmented generation evaluation'), a DOI (10.1038/s41586-021-03819-2), an arXiv ID (1706.03762), a PubMed ID (PMID:31452104) or a PMC ID (PMC6993921). One query per call; use 'queries' for a batch. ## `queries` (type: `array`): Optional list of extra queries, DOIs or IDs, processed one after another (max 100). ## `maxResults` (type: `integer`): How many papers to return per query, merged and de-duplicated across sources. ## `includeFullText` (type: `boolean`): Adds the paper's full text as Markdown when a legal open-access copy exists under a permissive licence (CC0, CC BY, CC BY-SA, public domain). Otherwise you get metadata, the licence and a link. Charged only when full text is actually delivered. ## `openAccessOnly` (type: `boolean`): Only return papers that are open access. ## `yearFrom` (type: `integer`): Optional earliest publication year. ## `yearTo` (type: `integer`): Optional latest publication year. ## `sources` (type: `array`): Which free scholarly databases to search. Europe PMC includes every PubMed record plus PMC full texts and preprints. ## `includeAbstracts` (type: `boolean`): Turn off for shorter output. ## Actor input object example ```json { "query": "large language model hallucination detection", "maxResults": 10, "includeFullText": false, "openAccessOnly": false, "sources": [ "arxiv", "crossref", "europepmc" ], "includeAbstracts": true } ``` # Actor output Schema ## `results` (type: `string`): No description # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "query": "large language model hallucination detection" }; // Run the Actor and wait for it to finish const run = await client.actor("poised_beardlichen/research-paper-search").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "query": "large language model hallucination detection" } # Run the Actor and wait for it to finish run = client.actor("poised_beardlichen/research-paper-search").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}") for item in client.dataset(run.default_dataset_id).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "query": "large language model hallucination detection" }' | apify call poised_beardlichen/research-paper-search --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "type": "http", "url": "https://mcp.apify.com/?tools=fetch-actor-details,poised_beardlichen/research-paper-search" } } } ``` The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer ` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations). ## OpenAPI specification Download the OpenAPI definition: https://api.apify.com/v2/actors/HfROKfiFevaQSGQkZ/builds/pBcDXAr8wkkSR9tvo/openapi.json