Scholarly stack

Claude With PubMed, OpenAlex, arXiv, Crossref, ORCID, and Zotero

Reliable AI research uses Claude around scholarly systems, not instead of them: databases retrieve records, registries verify metadata, libraries preserve citations, and Claude helps transform the resulting corpus into notes and synthesis.

Updated 2026-07-06

PubMed path NCBI E-utilities Use PubMed and Entrez exports for biomedical record retrieval before Claude triage. Graph search OpenAlex Use OpenAlex to map works, authors, sources, institutions, and topics at graph scale. Working memory Zotero library Store final accepted records in a library rather than letting source state live only in chat history.

A fully open catalog of the global research system.

PubMed: biomedical retrieval and controlled search

For biomedical literature, start in PubMed or NCBI E-utilities. Claude can help produce candidate search strings, identify MeSH-like vocabulary, and screen exported records, but the retrieval record should come from PubMed itself.

Save the search query, date, filters, result count, and export format. If Claude summarizes PubMed results, include PMIDs and article titles in the input so the output can be checked later.

OpenAlex: discovery across the research graph

OpenAlex is useful when the research question crosses disciplines or when you need works, authors, institutions, sources, topics, and citation relationships. Claude can help translate a plain-language question into OpenAlex filters or interpret exported records.

Use Claude for clustering and labeling, not as the authority on what the graph contains. Keep the OpenAlex query and response fields that produced the cluster.

arXiv and Crossref: preprints and DOI metadata

For fields where preprints matter, arXiv provides API access to e-print metadata. Ask Claude to triage arXiv records by methods and claims, then verify whether a preprint later has a journal DOI through Crossref or the publisher.

Crossref is the right metadata sanity check for DOI-bearing works. If Claude invents a volume, issue, author order, or publication year, Crossref is often the fastest way to catch it.

ORCID and Zotero: people and library state

ORCID helps disambiguate researchers when author names collide. Zotero helps preserve the library state after search and screening. Together they reduce one of the common failures of AI-assisted review: losing track of which "Smith 2024" or which exported record the summary actually refers to.

A practical pattern is: discover in databases, verify identifiers, store accepted sources in Zotero, export a clean bibliography, and then let Claude synthesize over that locked set.

Workflow checklist

  1. Ask Claude for candidate search terms and false-positive traps.
  2. Run the search in PubMed, OpenAlex, arXiv, Crossref, or field databases.
  3. Export records with stable identifiers.
  4. Use Claude to triage exported records and propose clusters.
  5. Verify metadata through registries.
  6. Store accepted records in Zotero or another reference manager.
  7. Use the curated library as Claude input for synthesis.

Researcher FAQ

Can Claude query these systems directly?

Sometimes through product features, connectors, MCP servers, or custom code. The core rule is still the same: preserve the query, response, and identifier trail.

Which database should I start with?

Start with the database your field treats as authoritative. PubMed is central for biomedical work, arXiv for many preprint-heavy technical fields, and OpenAlex for broad graph discovery.

Related workflows

Literature review protocol Lit Review A source-first workflow for using Claude in a literature review without losing PRISMA discipline, search provenance, or human judgment. Citation discipline Source Checking A practical protocol for checking Claude citations, web-search results, DOI metadata, Zotero libraries, and conflicting evidence. Prompt templates Prompts Prompt templates for literature search design, paper triage, evidence extraction, contradiction review, and reproducibility checks.