Skip to main content
Glama

Search the AnimatedWebs catalog

search_catalog
Read-onlyIdempotent

Searches the AnimatedWebs catalog (AnimatedWebs templates, UI library components, cinematic video backgrounds, website style references and verified creators) and returns metadata grouped by kind, never prompt text or source code. Use it first to find an identifier, then open one item with get_template, get_component, get_background, get_style_reference or get_creator; use list_categories for valid category values. An empty query browses a family in catalog order. Template and component queries match each word as a case-insensitive substring and rank by words matched (ties keep catalog order); background, style and creator queries match the whole text as one substring. Filters apply per kind (templates: category, access, templateKind, technique; components: category, runtime). With kind all a family that cannot use a supplied filter is skipped; with one kind an unusable filter is an error. Paging: each group has nextCursor (null on the last page); pass it back as cursor with the same kind, query and filters. Template results include views, saves and likes. Read-only. Example: {"query":"particles hero","kind":"templates","technique":"particles","limit":5}.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_catalog"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoWhich family to search: templates (AnimatedWebs templates), components (UI library), backgrounds (cinematic video loops), styles (website style references), creators, or all (default) for every family at once.all
limitNoMaximum results per family on this page. Defaults / ceilings: templates and components 10 / 50, backgrounds and styles 20 / 50, creators 10 / 30, kind all 6 / 20 per family. A value above the ceiling is lowered to it.
queryNoFree text. Empty or omitted browses the family in catalog order. Templates and components split it on spaces and match each word as a substring ('webgl particles hero'); backgrounds, styles and creators match the whole text as one substring ('nature', 'stripe', 'webgl').
accessNoTemplates only. free: prompts any signed-in account can fetch; pro: needs a Pro or Lifetime plan or a Prompt Pack credit.
cursorNoThe nextCursor of a previous result, unchanged, sent with the same kind, query and filters. Single kind only (not kind all).
runtimeNoComponents only. Exact runtime, case-insensitive, e.g. 'react', 'three' or 'css'.
categoryNoTemplates and components only. Templates: exact category, case-insensitive, from list_categories (kind templates), e.g. 'AI / SaaS'. Components: exact category from list_categories (kind components), e.g. 'Hero', 'Three.js', 'Buttons'. An unknown value returns no results.
techniqueNoTemplates only. A 3D / WebGL technique facet: threejs (three.js scenes), particles (particle fields), shaders (GLSL, raymarching, noise fields), 3d-objects (products to spin, inspect or configure), scroll-3d (scroll-driven 3D camera or scene) or simulators (machines, robots, physics). Same facets as animatedwebs.com/templates/3d.
templateKindNoTemplates only. website (full page), section (one page section), background (coded motion backdrop) or component.

Output Schema

NameRequiredDescriptionDefault
kindYesThe kind that was searched
stylesNo
creatorsNo
templatesNo
componentsNo
nextCursorYesSingle kind: the cursor for the next page, null on the last page. Always null for kind all; use each group's nextCursor instead.
backgroundsNo
unavailableNoKind all only: families that could not be searched right now

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description still adds real behavioral context: results are metadata grouped by kind and never include prompt text or source code, template results carry views/saves/likes, matching semantics differ per family, and an unusable filter is skipped under kind=all but an error under a single kind. That is substantive disclosure of edge-case and failure behavior.

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?

It is front-loaded with purpose and routing, then layers matching, filtering, and paging rules in a compact block with a worked example at the end. Nearly every sentence carries information, though the single dense paragraph makes the per-kind filter and paging rules harder to scan than a lightly structured version would be.

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?

For a 9-parameter, 4-enum search tool with an output schema, the description covers matching behavior, filter scope per kind, paging via nextCursor, and error conditions. Nothing an agent needs in order to call it correctly is missing, and return-shape detail is rightly delegated to the output schema.

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

Parameters3/5

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

Schema coverage is 100%, so the baseline is 3; the schema already documents kind, limit ceilings, query splitting, per-kind filter applicability and cursor reuse. The description adds cross-parameter behavior not in the schema (what happens to a filter a family cannot use under kind=all vs single kind) and a concrete example, which is an incremental gain over a schema that already does the heavy lifting.

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?

The description names a specific verb and resource ('Searches the AnimatedWebs catalog') and enumerates the five content families it covers. It also distinguishes itself from siblings by positioning itself as the identifier-discovery step before get_template, get_component, get_background, get_style_reference or get_creator.

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?

It gives explicit sequencing ('Use it first to find an identifier, then open one item with ...'), points to list_categories for valid category values, and explains the empty-query browse case. The when-to-use and which-alternative guidance is fully spelled out rather than implied.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.