paleobiology-mcp-server

paleobiology-mcp-server: get taxon record and fossil range

paleobiology_get_taxon

Read-onlyIdempotent

Resolve a taxon by name (e.g. "Tyrannosaurus") or by integer taxon_no to its accepted name, rank, higher classification, immediate parent, fossil occurrence count, and first/last appearance (FAD/LAD) range in millions of years — "when did this clade exist, and what is it." Run this first to resolve a name into the accepted name and taxon_no, then pass that id as base_id to paleobiology_search_occurrences, paleobiology_get_diversity, or paleobiology_search_collections for a clade-inclusive filter that carries no name ambiguity (the same id also appears as accepted_no on occurrence rows). Set show_children to also list immediate child taxa. PBDB taxonomy is opinionated and can differ from GBIF's backbone, so the accepted name may differ from the name you searched.

Input Schema

Name	Required	Description
`name`	No	Taxon name to resolve, e.g. "Tyrannosaurus" or "Ammonoidea". Provide this or taxon_no.
`taxon_no`	No	PBDB taxon id from a prior get_taxon, or accepted_no on an occurrence row. Provide this or name, never both.
`show_children`	No	When true, include a page of the immediate child taxa of this taxon (at most 200 per call — children_truncated says whether more remain).
`children_offset`	No	Number of immediate children to skip before the returned page — used only when show_children is true. Advance it by 200 while children_truncated is true to walk the whole child list.

Output Schema

Name	Required	Description
`rank`	No	Taxonomic rank, e.g. "genus", "family", "order".
`error`	No	Present when the call failed. Absent on success.
`extant`	No	True if the clade survives to the present day; false if entirely extinct.
`notice`	No	Guidance when the child list was cut off at the per-page cap (naming the children_offset that reaches the next page), or when children_offset ran past the end of the child list.
`children`	No	One page of immediate child taxa, at most 200 — present only when show_children was true. A taxon with more children than that returns a page, not the full list; read children_truncated before treating it as complete.
`taxon_no`	No	Accepted PBDB taxon id — the canonical id for this taxon. Pass it as base_id to paleobiology_search_occurrences, paleobiology_get_diversity, or paleobiology_search_collections to filter on this clade without re-sending a name.
`parent_no`	No	PBDB taxon id of the immediate parent, when known.
`attribution`	No	CC-BY data attribution for the Paleobiology Database.
`parent_name`	No	Name of the immediate parent taxon, when known.
`accepted_name`	No	PBDB accepted name (may differ from the searched name).
`classification`	No	Higher classification of the taxon. Each level is present only when PBDB resolves it.
`children_offset`	No	Position in the child list this page started at (0 is the first child). Present only when show_children was true.
`last_appearance`	No	A first- or last-appearance window. Empty when PBDB has no dated occurrences.
`first_appearance`	No	A first- or last-appearance window. Empty when PBDB has no dated occurrences.
`occurrence_count`	No	Number of fossil occurrences recorded in PBDB, when reported.
`children_truncated`	No	True when more immediate children remain past this page — re-call with children_offset advanced by 200 to read the next. False means this page runs to the end of the child list. Present only when show_children was true.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 15, 2026

changedInput schema / properties / taxon_no / description

Previous value: -"PBDB taxon id from a prior get_taxon, or accepted_no on an occurrence row. Provide this or name."New value: +"PBDB taxon id from a prior get_taxon, or accepted_no on an occurrence row. Provide this or name, never both."

changedOutput schema / properties / error / properties / data / properties / reason / description

Previous value: -"Machine-readable failure mode. Declared by this tool: `taxon_not_found`: The name or taxon_no resolved to no PBDB taxon. `missing_selector`: Neither name nor taxon_no was provided. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `taxon_not_found`: The name or taxon_no resolved to no PBDB taxon. `missing_selector`: Neither name nor taxon_no was provided. `conflicting_selector`: Both name and taxon_no were provided — the lookup takes exactly one selector. Other values are possible when a failure originates below the handler."

changedOutput schema / properties / error / properties / data / properties / reason / examples

Previous value: -[
-  "taxon_not_found",
-  "missing_selector"
-]New value: +[
+  "taxon_not_found",
+  "missing_selector",
+  "conflicting_selector"
+]

First observedSep 1, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already cover readOnly/idempotent/openWorld, so the description wisely focuses on what annotations cannot express: the PBDB-vs-GBIF backbone divergence and the caveat that accepted names may differ from the searched name. It also discloses that show_children paginates. Missing only explicit notes on auth/rate limits or error behavior for a nonexistent name.

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

Conciseness4/5

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

Front-loads the purpose with a quoted example, then the workflow guidance. Some density in the parenthetical FAD/LAD gloss is justified, but the sentence stack is long and could be slightly tighter.

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

Completeness5/5

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

With a 4-param read-only lookup that has a full output schema and complete schema coverage, the description supplies the missing conceptual layer—when to run it, what the id is for, and the taxonomic-backbone caveat—so an agent can act correctly without further information.

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; the description adds real value by explaining the show_children intent and the base_id reuse pattern, tying taxon_no to occurrence-row accepted_no. It does not re-explain the exclusive or-taxon_no/name constraint that the schema already enforces, which is fine.

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

Purpose5/5

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

Names a specific verb (resolve) and resource (taxon), and enumerates exactly what is returned: accepted name, rank, classification, parent, occurrence count, FAD/LAD. It is clearly distinguishable from the sibling search/diversity/collection tools.

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

Usage Guidelines5/5

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

Explicitly says 'Run this first' to resolve a name into accepted name + taxon_no, then names three specific siblings to pass base_id to, including the idempotent nature of the filter and its ambiguity-free benefit. Exclusions and sequencing are fully specified.

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

All paleobiology-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.