@cyanheads/worms-marine-taxa-mcp-server
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Contacts while installing and starting: nothing
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/worms-marine-taxa-mcp-server@0.2.0
Installing a package runs its code. Use a sandbox for anything you have not read.
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
worms_list_reference resultOffset, topic
List supported external identifier systems, a non-exhaustive taxonomic-status guide grouped as accepted, unaccepted, uncertain, or technical, environment-flag semantics, observed worms_get_distributions filter values, live taxonomic ranks, or live trait definitions. Resume nextResultOffset as resultOffset with the same topic. Identifier codes, statuses, environment flags, and distribution terms are available offline. A record status can be the specific reason itself, such as junior subjective synonym, rather than unaccepted. IUCN identifiers are not threat categories; null flags mean not recorded. Trait definitions retain complete-tree preorder indices across pages; parents may be on earlier pages.
worms_resolve_taxon inputOffset, matchOffset, resultOffset, names, vernacular, vernacularMatch, fuzzy, marineOnly, extantOnly, offset
Resolve exact or explicitly fuzzy scientific names, or search one vernacular name as a whole recorded common name or, with vernacularMatch: "contains", as part of one. Names default to marine-or-brackish and extant taxa; vernacular cannot filter. Resume scientific segments with nextInputOffset and nextMatchOffset against unchanged names and options; inputIndex preserves duplicates and partialGroup identifies split groups. For vernacular, consume nextResultOffset within the same upstream offset before advancing page.nextOffset and resetting resultOffset to zero. Full 50-match upstream groups remain completeness-unknown; accepted-name fields do not choose an ambiguous match.
worms_get_taxon inputOffset, vernacularOffset, sourceOffset, sourceUse, aphiaIds, includeVernaculars, includeSources
Retrieve full Aphia records by numeric IDs or canonical WoRMS LSIDs in byte-budgeted segments. Resume nextInputOffset as inputOffset using unchanged aphiaIds and options; inputIndex preserves duplicate and missing positions. includeVernaculars (common names) or includeSources (original description, basis of record, and other sources) requires one submitted ID, one of the two per call; resume nextVernacularOffset as vernacularOffset or nextSourceOffset as sourceOffset, repeating the full primary record. sourceUse filters whole use values ignoring case before sourceOffset; populated values are not trimmed. Successful source results report sourceTotalCount before slicing and unfilteredSourceCount only with an effective filter. Optional failure retains the record without source counts; unknown facts remain omitted or null.
worms_get_classification resultOffset, aphiaId, includeChildren, offset, marineOnly, extantOnly
Retrieve root-to-tip classification and optional direct children for an AphiaID or canonical WoRMS LSID. resultOffset indexes lineage followed by fetched children; consume nextResultOffset with unchanged options and upstream offset before advancing page.nextOffset and resetting resultOffset to zero. Missing ranks remain unknown; child offset and filters are inactive without includeChildren. A full fetched 50-row child page has uncertain continuation and can lead to an empty page. The submitted ID keeps its own recorded lineage; a notice names its linked accepted ID, distinguishing an accepted alternative representation from its preferred ID.
worms_get_synonyms aphiaId, offset, resultOffset
Retrieve synonyms for the accepted taxon linked from an AphiaID obtained with worms_resolve_taxon. Consume nextResultOffset within the same upstream offset before advancing page.nextOffset and resetting resultOffset to zero. A present name without an accepted ID has no synonym lookup; inspect it with worms_get_taxon. A full fetched 50-row page has uncertain continuation and may lead to an empty page.
worms_get_distributions recordStatus, establishmentMeans, invasiveness, occurrence, aphiaId, resultOffset, includeSynonyms, synonymOffset
Retrieve recorded distributions for an AphiaID or canonical WoRMS LSID in byte-budgeted segments; resume nextResultOffset as resultOffset with unchanged selectors and filters. WoRMS attaches records to individual name usages, so one AphiaID's rows can miss those of its synonyms: includeSynonyms combines the accepted taxon's rows with those of up to 10 synonyms per call, each row tagged sourceAphiaId; consume nextResultOffset before advancing synonymOffset to synonymUnion.nextSynonymOffset with resultOffset 0. Filters apply to the complete fetched set before pagination and combine by conjunction: recordStatus normalizes case and surrounding whitespace before exact matching; others use case-insensitive whole-value equality without trimming. Rows retain duplicates and source order; no rows does not prove biological or taxon absence. A notice names the linked accepted ID, distinguishing an accepted alternative representation from its preferred ID.
worms_get_traits resultOffset, aphiaId, includeInherited, measurementType
Retrieve recorded attributes for an AphiaID or canonical WoRMS LSID, including inherited attributes by default. Resume nextResultOffset as resultOffset with unchanged selectors and options. Whole rows retain original preorder nodeIndex and parentIndex across pages; parents may be on earlier pages. measurementType keeps each matching node with its subtree and ancestors, indices unchanged; totalCount counts that set and unfilteredCount the whole tree. Values, references and inheritance markers remain unchanged; on an accepted taxon WoRMS also returns attributes recorded on its synonyms whatever includeInherited is set to, marked by inheritedFrom. A notice names the linked accepted ID, distinguishing an accepted alternative representation from its preferred ID. Missing traits do not prove biological absence; IUCN list membership is not a threat category.
worms_crosswalk_id resultOffset, aphiaId, externalId, type
Crosswalk an AphiaID from worms_resolve_taxon to one or all nine external identifier systems, or reverse an externalId with required type to a full taxon record. Supply exactly one selector. Forward resultOffset indexes whole identifiers across types in requested order; resume nextResultOffset with unchanged selectors. typeTotals distinguishes successful absence from IDs on another segment; failed types remain separate. IDs stay opaque, including leading zeros and LSIDs. No IDs cannot establish taxon absence; IUCN identifiers are not threat categories.
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/worms-marine-taxa-mcp-server |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-nP2D2fbBNlXw91IslMqm5qYCBpVY/Lb+/Hc6AbXyTj4/0YYMTlCDzKMkgxB7O+95GMZUPGGNgkFrZTOFoyaRdw== |
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/worms-marine-taxa-mcp-server)
New version out? Ask for a fresh report.