Research Paper Search: OpenAlex, arXiv, PubMed and Crossref in one query

Search four major scholarly databases with a single query and get back one clean, deduplicated list of papers: titles, authors, year, venue, DOI, abstract, citation count and links to free PDFs or full text where they exist.

• 4 databases, 1 call: OpenAlex (all fields, citation counts), arXiv (preprints), PubMed (biomedicine) and Crossref (DOIs for almost every journal) are searched in parallel.
• Duplicates merged: a paper found in several databases appears once. Each copy fills in what the others are missing (abstract, PDF link, citation count, DOI).
• Ranked across databases: reciprocal rank fusion puts papers that rank high in several databases first. Sorting by newest or most cited is applied after merging, so results stay on topic.
• Fast and resilient: the four database searches finish in about 2-3 seconds, and a whole run, including start-up, takes about 7-10 seconds. If one database fails, the others still answer, and the run summary tells you which one failed.
• No API keys required. You can optionally add your own free OpenAlex key.
• Built for AI agents too: works through the Apify API and the Apify MCP server, so an agent can call it as a single literature-search tool.

Why one call beats four separate searches

Searching arXiv, PubMed, OpenAlex and Crossref separately means four queries, four result formats and a lot of duplicates: the same paper shows up as an arXiv preprint, a PubMed record and a Crossref DOI. Then you still have to work out which results matter most.

This tool does that work for you. It returns one schema for every paper, one record per paper, and one ranking that rewards papers several databases agree on. For an AI agent, that means one tool call and fewer tokens spent on duplicates.

Use cases

• Literature reviews and related-work sections
• Finding open-access PDFs for a topic (openAccessOnly: true)
• Biomedical evidence searches (PubMed together with journal and preprint coverage)
• Keeping up with recent preprints and papers in a field (sortBy newest, yearFrom)
• Finding the most cited papers on a topic
• Giving AI research assistants and RAG pipelines grounded sources with DOIs and abstracts

Input

Field	Type	Default	Description
query	string (required)		What to search for, in plain words, e.g. "CRISPR off-target effects"
sources	array	all four	Any of openalex, arxiv, pubmed, crossref
maxResults	integer	25	Papers returned after duplicates are merged. You pay per paper returned.
sortBy	string	relevance	Relevance puts papers ranked high in several databases first. Newest or most-cited sorting is applied after merging.
yearFrom	integer		Only papers published in or after this year
yearTo	integer		Only papers published in or before this year
openAccessOnly	boolean	false	Only return papers that are free to read
includeAbstracts	boolean	true	Turn off for shorter results (titles and links only)
openAlexApiKey	string		Optional free OpenAlex key, which gives you your own daily budget
contactEmail	string		Passed to OpenAlex, NCBI and Crossref so your requests use their faster "polite" pools

Input example

{
  "query": "climate change coral reefs",
  "sources": ["openalex", "arxiv", "pubmed", "crossref"],
  "maxResults": 25,
  "sortBy": "relevance",
  "yearFrom": 2005,
  "openAccessOnly": false,
  "includeAbstracts": true
}

Output

Each paper is one dataset item with these fields: rank, title, authors, year, publicationDate, venue, type, doi, url, pdfUrl, fullTextUrl, isOpenAccess, citationCount, abstract, ids (openalex, arxiv, pmid, pmcid), sources (which databases returned it) and query.

Output example (from a real test run; author list and abstract shortened here)

{
  "rank": 1,
  "title": "Coral Reefs Under Rapid Climate Change and Ocean Acidification",
  "authors": ["Ove Hoegh-Guldberg", "Peter J. Mumby", "A. J. Hooten", "..."],
  "year": 2007,
  "publicationDate": "2007-12-13",
  "venue": "Science",
  "type": "review",
  "doi": "10.1126/science.1152509",
  "url": "https://doi.org/10.1126/science.1152509",
  "pdfUrl": "https://openresearch-repository.anu.edu.au/bitstreams/ab9744aa-7521-4de0-8d87-55d2919d2206/download",
  "fullTextUrl": "https://openresearch-repository.anu.edu.au/bitstreams/ab9744aa-7521-4de0-8d87-55d2919d2206/download",
  "isOpenAccess": true,
  "citationCount": 5886,
  "abstract": "Atmospheric carbon dioxide concentration is expected to exceed 500 parts per million ...",
  "ids": { "openalex": "W2123920115", "pmid": "18079392" },
  "sources": ["openalex"],
  "query": "climate change coral reefs"
}

Each run also saves a SUMMARY record in its key-value store: which databases answered, how many papers each found, and how long each took.

Pricing

Pay per result: you are charged once for each paper returned (event paper-result). The current price per paper is shown on this page. Duplicates are merged before counting, so you never pay twice for the same paper. Use maxResults to control how many papers you get. The run stops cleanly when it reaches your maximum cost per run.

FAQ

Do I need API keys? No. Optionally, add a free OpenAlex key (from openalex.org) to get your own daily OpenAlex budget.

What happens if a database is down or rate-limited? The other databases still answer, and the run's SUMMARY record shows which one failed. Without a key, OpenAlex may sometimes refuse requests when its shared free budget runs out.

How are duplicates detected and merged? The same paper found in several databases becomes one record, and each copy fills in fields the others lack, such as abstract, PDF link, citation count and DOI. The sources field shows which databases found it.

Does it download full-text PDFs? No. It returns links (pdfUrl, fullTextUrl) to free versions when the databases know of one.

Can I search only one database? Yes. Set sources, e.g. ["pubmed"] for biomedicine only or ["arxiv"] for preprints only.

Can AI agents use it? Yes. Call it through the Apify API or add it as a tool through the Apify MCP server. The input is a plain-language query, and the output is one consistent JSON schema per paper.

How fast is it? The four database searches finish in about 2-3 seconds; a whole run, including start-up, takes about 7-10 seconds.