paleobiology-mcp-server

paleobiology-mcp-server: list geologic intervals

paleobiology_list_intervals

Read-onlyIdempotent

Look up the geologic time scale — eons, eras, periods, epochs, and ages with their absolute-age boundaries in millions of years (Ma) and nesting. This is the reference that grounds every temporal filter on the other tools and translates a named interval like "Late Cretaceous" to its 100.5–66.0 Ma boundaries (and back). Filter by a name substring, a Ma range (overlap match), and/or a level; call with no filters to browse the full scale. Browsing and every name on the bundled ICS international-scale snapshot are answered offline. A name the snapshot does not carry — the sub-stage and regional names that occurrence and collection rows report, such as "Late Maastrichtian" or "Lancian" — costs one PBDB lookup across its other time scales; the response names which source answered and which scale the interval belongs to.

Input Schema

Name	Required	Description
`name`	No	Case-insensitive substring of the interval name, e.g. "cretaceous" or "Jurassic". A name the bundled international scale does not carry is matched exactly against PBDB's other time scales.
`level`	No	Restrict to one rank of the international scale: eon, era, period, epoch, or age (finest). Browsing is bounded to that scale, so the sub-stage and regional ranks are not selectable here.
`max_ma`	No	Older bound of an age window (Ma); intervals overlapping [min_ma, max_ma] match. When paired with min_ma it must be greater than or equal to it — equal bounds name a single point in time.
`min_ma`	No	Younger bound of an age window (Ma); intervals overlapping [min_ma, max_ma] match.

Output Schema

Name	Required	Description
`error`	No	Present when the call failed. Absent on success.
`notice`	No	Guidance when no interval matched the filters.
`source`	No	Which source answered: "bundled_ics" for the offline international-scale snapshot, "pbdb_upstream" for a name resolved live against PBDB's other time scales.
`intervals`	No	Matching geologic intervals, sorted oldest-first.
`totalCount`	No	Number of intervals matched by the filters.
`snapshot_version`	No	ICS chart version and generation date of the bundled time scale, for citation.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 15, 2026

changedInput schema / properties / max_ma / description

Previous value: -"Older bound of an age window (Ma); intervals overlapping [min_ma, max_ma] match."New value: +"Older bound of an age window (Ma); intervals overlapping [min_ma, max_ma] match. When paired with min_ma it must be greater than or equal to it — equal bounds name a single point in time."

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

Previous value: -"Machine-readable failure mode. Declared by this tool: `interval_not_found`: A named interval filter matched nothing — neither the bundled international scale (after any level or Ma filters) nor a PBDB lookup across its other time scales. `interval_lookup_unavailable`: The name is outside the bundled international scale and the PBDB lookup that covers the other time scales could not be reached. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `interval_not_found`: A named interval filter matched nothing — neither the bundled international scale (after any level or Ma filters) nor a PBDB lookup across its other time scales. `interval_lookup_unavailable`: The name is outside the bundled international scale and the PBDB lookup that covers the other time scales could not be reached. `inverted_ma_range`: max_ma was smaller than min_ma — the age window is inverted. Other values are possible when a failure originates below the handler."

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

Previous value: -[
-  "interval_not_found",
-  "interval_lookup_unavailable"
-]New value: +[
+  "interval_not_found",
+  "interval_lookup_unavailable",
+  "inverted_ma_range"
+]

First observedSep 1, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations cover only safety/idempotency; the description adds substantial behavioral context beyond them: bundled ICS snapshot names are answered offline, non-snapshot names cost one PBDB lookup across other time scales, and the response discloses which source answered and which scale the interval belongs to. This is exactly the kind of provenance/latency detail annotations cannot carry.

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?

Purpose and routing are front-loaded in the first two sentences, and the offline-vs-PBDB caveat follows logically. It runs long and repeats some schema phrasing about sub-stage/regional names, but nearly every clause carries usable information.

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-shape explanation isn't required, and the description covers filters, offline/lookup behavior, and source provenance. It omits result ordering and whether a full-scale browse is paginated, which would matter for the 'no filters' case.

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 the baseline is 3, but the description adds genuine meaning: Ma filters are overlap matches over [min_ma, max_ma], equal bounds denote a single point in time, and the level enum is bounded to the international scale so sub-stage/regional ranks are not selectable. Minor redundancy with schema text keeps it from a 5.

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?

States a specific verb and resource (look up the geologic time scale: eons through ages with Ma boundaries and nesting) and its role as the reference grounding temporal filters on other tools. It is clearly distinct from the sibling search/diversity/reference tools.

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

Usage Guidelines4/5

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

Explicitly describes the three filter modes (name substring, Ma overlap range, level) and that calling with no filters browses the full scale, plus the fallback behavior for names not in the snapshot. It doesn't name sibling tools or exclusions, but no alternative is really needed here since the lookup routing is handled internally.

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.