Academic Research MCP: Papers, Citations & Authors

Search 250 million+ scholarly papers from Claude, Cursor or any other MCP client, or in a normal Apify run. Every paper comes with its title, authors, year, venue, DOI, citation count, open-access PDF link and topics, and get_paper adds the abstract. Your agent can also follow the citation graph both ways, list a researcher's papers, and get a one-call overview of a topic.

The data comes from OpenAlex, the open catalogue of scholarly works (journal articles, conference papers, books and preprints, arXiv included). When OpenAlex can't answer a search, Crossref answers it instead.

Every paper has a real DOI or OpenAlex ID, so an agent can cite sources instead of inventing them.

Tools

Tool	What it does
search_papers	Papers whose title or abstract match a query. Sort by relevance, citations or newest; filter by year range and open access
get_paper	One paper by DOI, OpenAlex ID or arXiv ID, with its abstract, citation and reference counts, and whether it was retracted
citing_papers	Papers that cite a paper (forward citations): follow-up work, replications, critiques
references	The papers a paper cites (its bibliography), most cited first
author_papers	A researcher by name, ORCID or OpenAlex ID: their institution, h-index, total citations and top papers. Lists other authors with the same name
literature_report	A topic overview in one call: the most cited, most relevant and newest papers, papers per year, leading venues, authors and topics, the open-access share, and any retracted papers in the sample

A call returns at most 50 papers. Each paper looks like this:

{
  "title": "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks",
  "doi": "10.48550/arxiv.2005.11401",
  "year": 2020,
  "date": "2020-05-22",
  "type": "preprint",
  "venue": "arXiv (Cornell University)",
  "authors": ["Patrick Lewis", "Ethan Perez", "Aleksandra Piktus", "…"],
  "citedBy": 3048,
  "referencesCount": 59,
  "openAccess": true,
  "openAccessUrl": "https://arxiv.org/pdf/2005.11401",
  "url": "https://doi.org/10.48550/arxiv.2005.11401",
  "topics": ["Safety Systems Engineering in Autonomy", "Ethics and Social Impacts of AI", "Adversarial Robustness in Machine Learning"],
  "retracted": false,
  "openalexId": "W3027879771",
  "source": "openalex"
}

Connect your agent

Use the MCP URL from this Actor's Endpoints tab (it ends in /mcp) and your Apify API token. For Claude Code:

claude mcp add --transport http academic-research https://<username>--academic-research-mcp.apify.actor/mcp \
  --header "Authorization: Bearer <your Apify API token>"

Other clients (Claude Desktop, Cursor, Windsurf, VS Code) take the same URL and the same headers in their JSON config. Then ask your agent something like:

• "Find the 10 most cited papers on microplastics in drinking water since 2018 and summarize what they agree on."
• "Who cites 10.1038/nature12373? Show the newest five."
• "Give me a literature overview of CRISPR off-target effects."
• "List Jennifer Doudna's most cited papers."

Apify starts the server when your agent calls it and stops it when it goes quiet, so nothing runs while you don't use it.

Normal runs (no MCP client needed)

Click Start with a search query, a list of paper IDs, or both. Each paper becomes one row in the dataset, ready to download as CSV, Excel or JSON.

• Search: a query, an optional year range, open-access-only, sort order, and up to 1,000 papers.
• Look up IDs: paste DOIs, OpenAlex IDs or arXiv IDs to get their metadata, abstracts and citation counts (for example, to enrich a reference list). IDs that aren't found are listed in the run's status and cost nothing.

Pricing

Pay per event: you pay only for what works.

Event	Price (Free plan)
MCP tool call (search_papers, get_paper, citing_papers, references, author_papers)	$0.008
literature_report (three searches merged)	$0.03
One paper saved in a normal run	$0.002

Bronze, Silver and Gold subscribers pay 10%, 20% and 30% less. Failed calls are free. Apify's platform usage is included in these prices.

OpenAlex API key (optional)

OpenAlex gives every API user a daily budget. Single-paper lookups are free; searches use the budget. Without a key, your searches share this Actor's budget, and when it runs out for the day, searches come from Crossref instead (the answer says so). Crossref has no open-access links or topics and can't filter by open access.

For your own budget, get a free key at openalex.org/settings/api and send it in the X-OpenAlex-Api-Key header (add --header "X-OpenAlex-Api-Key: <key>" to the command above), or put it in the Actor's input for normal runs. It is stored encrypted.

Good to know

• Coverage: OpenAlex covers journals, conferences, books, repositories and preprint servers in every field. Citation counts are OpenAlex's own and can differ from Google Scholar's or Scopus's.
• Duplicates: a preprint and its published version are separate records upstream. Searches keep the better-ranked one and fill in its DOI from the other.
• Topics: OpenAlex assigns them by machine and they are sometimes off (the example above is a real record).
• Abstracts: come from OpenAlex where the publisher made them available; some papers have none.
• Full texts: this Actor returns links to free full texts (openAccessUrl); it doesn't download PDFs.
• arXiv: arXiv papers are included through OpenAlex. This Actor doesn't call arXiv's own API.
• Data licences: OpenAlex data is CC0. Crossref metadata is open for reuse. This Actor isn't affiliated with or endorsed by OpenAlex, Crossref or arXiv.

Support

Found a problem or need another field or tool? Open an issue in the Issues tab; I read every one.