worms-marine-taxa-mcp-server

Worms Get Classification

worms_get_classification

Read-onlyIdempotent

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.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "aphiaId": "<aphiaId>"
    },
    "name": "worms_get_classification"
  }
}

Input Schema

Name	Required	Description
`offset`	No	One-based starting record, advancing by 50; default 1.
`aphiaId`	Yes	Positive safe-integer AphiaID, decimal string, or canonical urn:lsid:marinespecies.org:taxname:<AphiaID>; outputs remain numeric.
`extantOnly`	No	Extant children only; inactive without includeChildren.
`marineOnly`	No	Marine or brackish children only; inactive without includeChildren.
`resultOffset`	No	Zero-based position in lineage followed by fetched children; keep upstream offset unchanged until nextResultOffset is null.
`includeChildren`	No	Also fetch one page of direct children.

Output Schema

Name	Required	Description
`echo`	No	Effective options; child-only options inactive when includeChildren is false.
`page`	No	Children pagination only.
`error`	No	Present when the call failed. Absent on success.
`found`	No	Whether classification exists.
`ranks`	No	This segment of the root-to-tip lineage.
`notice`	No	Linked accepted/preferred-AphiaID and empty-children-page guidance, in that order.
`aphiaId`	No	Positive safe-integer AphiaID; obtain from worms_resolve_taxon.
`children`	No	One page of direct children when requested and retrieved.
`guidance`	No	Next step for absent classification.
`byteBudget`	No	Complete serialized response byte target.
`totalCount`	No	Known local sequence length before pagination.
`attribution`	No	WoRMS source attribution.
`statusError`	No	Failed taxonomic-status read; evidence is unaffected, but whether the AphiaID is its accepted name is unknown.
`resultOffset`	No	Zero-based starting position in the complete local sequence.
`budgetLimited`	No	Whether the byte budget ended this local page early.
`childrenError`	No	Optional children retrieval failure.
`oversizedItem`	No	One indivisible scientific item exceeds the target; retained intact with forward progress.
`requiredBytes`	No	Serialized paired-surface result bytes for an oversized item, excluding transport-added metadata.
`returnedCount`	No	Whole scientific items returned on this segment.
`nextResultOffset`	No	Next local position; null when consumed.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 29, 2026

changedInput schema / properties / marineOnly / description

Previous value: -"Marine children only; inactive without includeChildren."New value: +"Marine or brackish children only; inactive without includeChildren."

First observedOct 24, 2026

TDQS

A3.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/openWorld, but the description adds real behavioral context beyond them: a full 50-row child page has uncertain continuation and may yield an empty page, missing ranks stay 'unknown', and a notice names the linked accepted ID. These are non-obvious traits an agent would otherwise have to discover by trial. Slightly dense phrasing but substantive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded, but the remainder is a dense run-on chain of pagination mechanics and a convoluted closing sentence about the accepted-ID notice. Every topic is relevant, yet the packing makes it hard to scan; it could be decomposed into clearer steps.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be explained, and the description covers the tricky parts: three offset layers, filter deactivation, uncertainty at page boundaries, and accepted-vs-submitted ID behavior. What's missing is selection guidance against sibling tools, which is a separate dimension.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds cross-parameter semantics the schema does not: resultOffset indexes lineage followed by fetched children, and extantOnly/marineOnly plus child offset are inactive without includeChildren. That interplay is genuinely useful beyond the per-field schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'retrieve root-to-tip classification and optional direct children for an AphiaID or canonical WoRMS LSID.' That is clearly distinct from siblings like worms_get_taxon or worms_get_distributions. It doesn't explicitly name a sibling or state when it's the right choice, keeping it just below a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Guidance is mechanical rather than selection-oriented: it explains how to page ('consume nextResultOffset with unchanged options...') and when child offset/filters are inactive, but never says when to reach for this tool instead of worms_get_taxon or worms_get_synonyms. Usage is implied through the pagination protocol, not the tool's role.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All worms-marine-taxa-mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.