Tools

Six tools for working with bioRxiv and medRxiv preprint data:

biorxiv_get_preprint

Fetch preprint metadata by DOI — all revisions in one call.

• Batch fetch up to 10 DOIs in a single request
• Each DOI returns the full revision history in collection[] — one API call per DOI, no enumeration loop
• Includes title, authors, abstract, category, license, JATS XML full-text link (jatsxml), and published journal DOI when the preprint has been accepted
• Scope to biorxiv, medrxiv, or both; when both, each DOI fans out in parallel and partial failures report per-DOI in failed[]
• Each failed[] entry carries a reason (not_found, invalid_doi_format, upstream_unavailable, rate_limited) and a retryable flag — a DOI is only reported as not found when every attempted server answered
• A lookup the origin rate-limited (HTTP 429) reports as rate_limited rather than folding into upstream_unavailable, and carries retryAfter — the wait in seconds api.biorxiv.org asked for

biorxiv_list_recent

Page through preprints in a date interval.

• Server-side category filtering via ?category=… — pass a value from biorxiv_list_categories
• Fixed page size of 30 (API constraint); advance with integer cursor (0, 30, 60, …)
• Response includes total count per server for calculating remaining pages
• When server="both", each server paginates independently; response surfaces per-server pagination state ({ biorxiv: { cursor, total }, medrxiv: { cursor, total } })
• A server whose cursor is past its last page is marked exhausted: true — the API reports total: 0 for an out-of-range cursor, so that count is an artifact rather than the interval total
• One server not answering under server="both" is named in failed[] rather than dropped; the other server's page is still returned, and a non-empty failed[] marks the result set as partial
• Every attempted server failing raises a retryable upstream_unavailable (or rate_limited) error instead of returning an empty page — nothing answered, so an empty interval was never established

biorxiv_search_preprints

Keyword and/or author search with relevance ranking.

• EuropePMC powers relevance ranking (indexes new preprints within 1–2 days of posting); bioRxiv/medRxiv API provides canonical metadata enrichment
• Optional author maps to an EuropePMC AUTH:"…" field query, ANDed with the keyword query — supply query, author, or both
• Covers both servers by default; scope down with server
• Optional date range filters (date_from, date_to)
• Enriched results carry the same latest-revision fields biorxiv_get_preprint returns — including type, license, funder, and authorCorrespondingInstitution
• Enrichment failures degrade gracefully to EuropePMC-only metadata, surfaced via partial_results and a per-record enrichment_error (service_error, rate_limited, or not_found)
• A EuropePMC rate limit (HTTP 429) raises a retryable rate_limited error carrying the origin's Retry-After wait — the search is the primary call and has no metadata to fall back on, unlike the enrichment step

biorxiv_get_published_version

Resolve a preprint DOI to its journal publication crosswalk.

• Uses the /pubs/{server}/{doi} endpoint for richer metadata than the publishedJournalDoi field in biorxiv_get_preprint
• Returns journal DOI, journal name, published date, and corresponding author institution
• Use when the preprint's publishedJournalDoi field is present and you need the full crosswalk record
• Scope to biorxiv, medrxiv, or both; both is the default because the two servers share the 10.1101/ DOI prefix, and the output server field names the one that answered
• No server answering raises a retryable upstream_unavailable, or rate_limited with the origin's wait when the failure was an HTTP 429 — never doi_not_found, which would assert an absence nothing established

biorxiv_get_fulltext

Retrieve a preprint's full text as best-effort Markdown.

• Fetches the rendered HTML article page (www.{server}.org/content/{doi}v{N}.full) and extracts Markdown — there is no keyless JATS source
• Resolves the latest version via the details API first, for the URL version and clean not-found handling
• Scope to biorxiv, medrxiv, or both; both is the default because the two servers share the 10.1101/ DOI prefix. Only the DOI resolution fans out — the full-text fetch targets the single server that answered, named in the output server field
• Long articles page via offset/limit character chunking (totalChars, remainingChars, hasMore); the extracted article is cached per version, so paging costs one origin fetch rather than one per chunk
• PDF-only preprints and blocked/challenge pages return a typed fulltext_unavailable error routing to biorxiv_get_preprint
• An origin rate limit (HTTP 429) returns a retryable rate_limited error carrying the origin's Retry-After wait, rather than a bare fetch failure. Both origins this tool touches can hit it — the article page during the full-text fetch, api.biorxiv.org during version resolution — and the recovery hint names which of them are limiting, since biorxiv_get_preprint is only a useful fallback while the metadata origin is answering

biorxiv_list_categories

Return the static subject category taxonomy for both servers.

• No API call — hardcoded static list (~30 bioRxiv + ~50 medRxiv categories)
• Use to validate category strings before passing to biorxiv_list_recent

Features

Built on @cyanheads/mcp-ts-core:

• Declarative tool definitions — single file per tool, framework handles registration and validation
• Unified error handling across all tools
• Pluggable auth (none, jwt, oauth)
• Swappable storage backends: in-memory, filesystem, Supabase, Cloudflare KV/R2/D1
• Structured logging with optional OpenTelemetry tracing
• STDIO and Streamable HTTP transports

bioRxiv-specific: