Research Chain MCP server

@pipeworx/research-chain

Everything openly available around one academic paper, in a single call: full text, license, datasets, code, and citations. Given a DOI, PMID, or arXiv id, research_chain walks the join that Crossref, OpenAlex, Unpaywall, DataCite, Zenodo, Hugging Face Papers, PubMed Central, and Semantic Scholar each expose piecemeal — so a caller no longer has to know all six/seven tools to answer "what datasets and code are linked to this paper?" or "find an open copy of this DOI and its license."

Part of Pipeworx — an MCP gateway connecting AI agents to 1576+ live data sources.

Tools

returns:

• researchchain({doi | pmid | arxivid, maxdatasets?, maxciting?}) —

(URL + which manuscript version each applies to), OpenAlex concepts and citation count.

• paper — title, journal, publisher, authors, Crossref's stated license(s)

with its OWN hosttype, version (publishedVersion | acceptedVersion | submittedVersion), and license — never collapsed. isoa: true only means "a free-to-read copy exists somewhere"; it says nothing about reuse rights, which is why license is null (not guessed) whenever Unpaywall doesn't state one. A PubMed Central copy (if one exists) is added as its own entry with license and version explicitly null, since NCBI's ID Converter confirms the copy exists but doesn't state its terms.

• open_copies[] — every open-access location Unpaywall knows about, each

Converter.

• pmcfulltext — {hasfulltext, pmcid, pmid, url} from NCBI's ID

relatedIdentifiers search (datasets/software that cite the paper's DOI). total is the real upstream count even when results is truncated to max_datasets.

• datasets — {total, returned, results[]} from DataCite's

metadata.relatedidentifiers.identifier. paperswithcode (Hugging Face Papers, the de-facto successor) reports {found: false, results: []} when the upstream search comes back empty — an empty result is notfound, never treated as an answer (a bare [] from this upstream used to be routed to as if it were a real "no code exists" answer).

• code — {zenodo[], paperswithcode}. Zenodo is searched by

paper's total citation count, top is up to max_citing citing papers sorted by their own citation count. note carries an honest partial- failure message (e.g. a rate limit) when one of the two Semantic Scholar calls failed but the other succeeded — it is never silently dropped.

• citing — {count, top[], note} from Semantic Scholar: count is the

paper (title marker, update-to retraction notices, is-retracted-by relation) — no extra API call. retracted: false means "no retraction on record", not proof the paper is clean (coverage depends on the publisher).

• retraction — derived from the SAME Crossref record already fetched for

in parallel; a slow or dead upstream lands in sources_failed with a reason, and every other leg still returns.

• sourcesused / sourcesfailed — every leg fetches independently and

• as_of — ISO timestamp of the call.

Auth

Keyless. Every upstream here is a public, unauthenticated API. Crossref, OpenAlex, and the NCBI ID Converter ask only for a polite-pool contact email, which this pack supplies as its own (hello@pipeworx.io) — the same pattern as the crossref, openalex, and unpaywall packs.

Data sources

Shortened. The full README is on GitHub.