datacite-mcp-server
Server Details
Search DataCite datasets and software, fetch DOI metadata, trace relations, format citations.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- cyanheads/datacite-mcp-server
- GitHub Stars
- 1
- Server Listing
- @cyanheads/datacite-mcp-server
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
Each tool targets a distinct operation: single-DOI citation rendering, single-DOI metadata retrieval, relation-graph traversal, work search, repository search, and offline vocabulary lookup. The only adjacency (get_work vs. trace_relations) is explicitly clarified, with get_work scoped to metadata fields and trace_relations to the graph, and get_work even points at trace_relations for graph work.
All six tools follow a uniform datacite_<verb>_<noun> pattern (get_citation, get_work, list_reference, search_repositories, search_works, trace_relations). Verb choice is meaningful and consistent: get for single-record fetch, search for discovery, list for reference data, trace for graph traversal.
Six tools is well-scoped for a read-only DataCite metadata server: discovery (works, repositories), retrieval (work), rendering (citation), graph (relations), and reference/vocabulary lookup. No tool appears redundant or like filler, and the surface is not so thin that agents hit obvious dead ends.
The read-only lifecycle is well covered — search, fetch, cite, relate, and vocabulary resolution all have a home, with facets, cursor paging, and version scoping handled. Minor gaps remain: no direct client/provider entity listing or usage/event reporting endpoint beyond what get_work and trace_relations surface, and no write/mint operations (likely intentional for a read-only server).
Available Tools
6 toolsdatacite_get_citationGet DataCite citationARead-onlyIdempotentInspect
Render one DataCite DOI as a formatted citation in a CSL style and locale (APA in US English by default), or as a machine-readable record: CSL JSON, BibTeX, RIS, DataCite JSON or XML, Schema.org JSON-LD, Codemeta, or JATS. A style the upstream renderer does not support — an unknown id or a dependent journal style — is rejected instead of silently rendered as APA. Formatted text comes back as plain text alongside the upstream HTML markup. A long document comes back one slice at a time: limit sets the slice size in UTF-16 units (default 100,000) and nextOffset continues it. A DOI DataCite does not hold returns found: false naming the registration agency that does.
Inputs: doi (required), limit, style, format, +2 more. Returns: cap, doi, error, found, +15 more
datacite_get_workGet DataCite workARead-onlyIdempotentInspect
Fetch the full deposited DataCite metadata for one DOI: titles, creators and contributors with ORCID iDs and ROR affiliations, publisher, dates, version, subjects, descriptions, funding, geolocations, rights, sizes and formats, related identifiers with their relation types, repository and provider, and citation, reference, version, part, view, and download counts. Long lists are capped with exact list/offset continuation recipes; select a list to retrieve later entries without losing the other metadata, or relation_types to page only the related identifiers of chosen relation types. datacite_trace_relations maps a bounded graph (at most 100 nodes and 1,000 edges). A DOI DataCite does not hold returns found: false naming the registration agency that does, or saying the DOI does not exist.
Inputs: doi (required), list, offset, relation_types. Returns: doi, dates, error, found, +36 more
datacite_list_referenceDataCite reference vocabulariesARead-onlyIdempotentInspect
Look up the controlled vocabularies and identifier forms the other datacite_* tools accept: resource types, relation types with their inverses and groups, related-identifier types, date and contributor types, fields of science, common license ids, repository types, certificates, software platforms, client types, sort orders, query-syntax field paths, citation formats, verified citation styles and locales, accepted identifier forms (DOI, ORCID iD, ROR ID, Crossref Funder ID, country, language, repository, and provider ids), and coverage and rate-limit rules. Offline; makes no upstream request.
Inputs: topic (required). Returns: error, notes, title, topic, +1 more
datacite_search_repositoriesSearch DataCite repositoriesARead-onlyIdempotentInspect
Find DataCite repository accounts by name or description text, field of science, repository type, certification (e.g. CoreTrustSeal), software platform, client type, or parent provider, or look up known repository IDs. Returns each repository's repositoryId — the value datacite_search_works takes in repository_ids — with its providerId, name, type, certificates, software, subjects, homepage, and re3data link. To rank repositories by how many works they hold on a topic, run datacite_search_works with that topic and include_facets: true; its repositories facet lists the top ten with counts.
Inputs: page, limit, query, software, +6 more. Returns: error, notice, nextPage, totalCount, +4 more
datacite_search_worksSearch DataCite worksARead-onlyIdempotentInspect
Search DataCite DOI metadata for datasets, software, samples, workflows, and other research outputs. Combine plain words (text) or OpenSearch query syntax (query) with filters for resource type, creator (ORCID iD or name), affiliation (ROR ID or name), affiliation country, funder (ROR ID, Crossref Funder ID, or name), subject, field of science, repository, provider, license, language, geographic place, publication-year range, and minimum citation count. Returns the total match count and compact rows — DOI, title, first creators, year, type, repository, licenses, and citation/view/download counts — plus optional top facet counts. The total counts DOIs, so a versioned work counts once per DOI — its concept DOI and each version DOI, as Zenodo registers them; set version_scope to series to count each version series once, or releases to count only the versions. Page numbers reach the first 10,000 ranked matches; pass cursor "*" to walk any result set in full, in registration order.
Inputs: page, sort, text, limit, +20 more. Returns: error, works, facets, notice, +7 more
datacite_trace_relationsTrace DataCite relationsARead-onlyIdempotentInspect
Map the relation graph around one DOI — versions, parts, supplements, derivations, documentation, citations, references, and every other DataCite relation type — as nodes and directed edges that keep the relationType exactly as asserted and name each edge's source: the DOI's own metadata, other DataCite records that point at it, or DataCite Event Data (citation links harvested from Crossref and other sources). Accepts any DOI, including a journal article's DOI, to find the datasets and software it cites and those that cite, supplement, or derive from it. DataCite DOIs are hydrated with title, type, year, repository, and citation count; other identifiers stay leaf nodes. Depth 1 by default, at most 2, with a node cap (default 50, max 100) disclosed when it binds. An absent edge is not evidence that no relationship exists.
Inputs: doi (required), depth, max_nodes, event_offset, +2 more. Returns: cap, root, edges, error, +7 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Search and resolve Zenodo datasets, software, and publications by DOI; trace versions and funding.
Resolve DOIs, search ~188M scholarly works, and fetch references via the Crossref REST API.
Search 150M+ academic works, journals, and funders via Crossref API.
DataCite MCP — DOIs for research datasets (free, no auth)
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides access to DataCite DOIs for research datasets, enabling searching and retrieval of dataset metadata.83 npmMIT
- AlicenseAqualityAmaintenanceSearches and fetches research datasets across Zenodo, DataCite (Dryad/Figshare/Dataverse/OSF), NCBI omics archives (GEO/SRA/BioProject), and the literature (PubMed/OpenAIRE) through one normalized model — deduplicating by DOI, expanding organism queries with NCBI Taxonomy synonyms, and bridging papers to the datasets they produced. Resolves citations and open-access full text, and downloads files.6349 PyPI4MIT
- FlicenseAqualityCmaintenanceProvides read-only access to DataCite's index of 125M+ research DOIs via natural language queries, enabling searching, metadata retrieval, citation formatting, and relationship exploration.9-
- AlicenseNot gradedqualityCmaintenanceEnables querying citation data from OpenCitations, including references, citations, citation counts, and bibliographic metadata for DOIs.93 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.