@cyanheads/datacite-mcp-server
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Returns a result when called with no setup: 2 of 2 tools tried
Contacts while installing and starting: nothing
Its tool definitions changed since version 0.2.1. If you approved the earlier ones, read them again.
What it contacted
Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.
Starting it
npx -y @cyanheads/datacite-mcp-server@0.2.2
Installing a package runs its code. Use a sandbox for anything you have not read.
Calling its tools
2 tools that take no input and look read-only were called once with nothing. 2 returned a result.
datacite_search_works | Returned a result 1.6 s · 16,207 characters |
datacite_search_repositories | Returned a result 0.3 s · 16,860 characters |
During the calls (not necessarily because of them) it first contacted: api.datacite.org.
Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
datacite_search_works text, query, resource_types, creator, affiliation, affiliation_country, funder, include_child_funders, subject, fields_of_science, repository_ids, provider_ids, licenses, language, place, published_from, published_to, min_citations, version_scope, sort, limit, page, cursor, include_facets
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.
datacite_get_work list, relation_types, offset, doi
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.
datacite_trace_relations doi, depth, relation_types, event_offset, include_event_data, max_nodes
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.
datacite_search_repositories query, field_of_science, repository_types, certificates, software, client_type, provider_id, repository_ids, limit, page
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.
datacite_get_citation doi, format, style, locale, offset, limit
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.
datacite_list_reference topic
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.
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Install facts
| License | Apache-2.0 |
|---|---|
| Needs | node >=24.0.0 |
| Source | github.com/cyanheads/datacite-mcp-server |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-PrDw1Mraa6f43meyuCk+vGlRezKjgoVsi/VaANvRL5IVXbZyveQnJZym4n/AefgqSXBTox8mfQPzqHnitXp/UA== |
Versions reported
| Version | Run | Result | Tools |
|---|---|---|---|
| 0.2.2 | 2026-11-16 | Starts with no setup | 6 |
| 0.2.1 | 2026-11-12 | Starts with no setup | 6 |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/%40cyanheads/datacite-mcp-server)
New version out? Ask for a fresh report.