Zyla API Hub

browse_catalog

Browse the full Zyla API Hub catalog with pagination. Use this to explore ALL public APIs beyond the top 500. Supports filtering by category and search keyword. Returns paginated results with total count and page info. Results come already ranked: the default "featured" sort is the marketplace order (relevance_score, refreshed daily), so take the list as-is to pick the top APIs.

Input Schema

Name	Required	Description
`page`	No	Page number (default: 1)
`sort`	No	Sort order: "featured" (marketplace Featured order by relevance_score), "popularity" (usage only), "newest", or "name" (default: featured)
`search`	No	Search keyword to filter APIs by name or description (server-side search across ALL public APIs)
`category`	No	Filter by category name (use list_categories to see available categories)
`per_page`	No	Results per page (default: 20, max: 100)
`include_params`	No	If true, include full endpoint parameters in the response (default: false, to keep responses compact)

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 21, 2026

changedInput schema / properties / sort / description

Previous value: -"Sort order: \"popularity\", \"newest\", or \"name\" (default: popularity)"New value: +"Sort order: \"featured\" (marketplace Featured order by relevance_score), \"popularity\" (usage only), \"newest\", or \"name\" (default: featured)"

changedInput schema / properties / sort / enum

Previous value: -[
-  "popularity",
-  "newest",
-  "name"
-]New value: +[
+  "featured",
+  "popularity",
+  "newest",
+  "name"
+]

First observedJul 8, 2026

TDQS

A3.6/5.0

Behavior3/5

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

No annotations exist, so the description carries the full burden. It usefully discloses pagination, that results arrive pre-ranked, the semantics of the default "featured" sort, and that relevance_score refreshes daily. It omits auth requirements, rate limits, and explicitly confirming the operation is a safe read, leaving gaps for a no-annotation tool.

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?

Four sentences, purpose front-loaded, each adding distinct information (scope, filtering, return shape, ranking rationale). Minor redundancy between "with pagination" and "Returns paginated results with total count and page info" keeps it from a 5.

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 no output schema, the description does compensate by stating the return shape (paginated results with total count and page info). With no annotations, read-only safety is only implied by "Browse" and auth is unaddressed, so it is not fully complete.

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 3 applies, but the description adds genuine meaning beyond the schema: it explains why the default "featured" order should be taken as-is and that relevance_score is refreshed daily. It also cross-references list_categories for the category parameter, which the schema only does partially.

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?

States a specific verb and resource ("Browse the full Zyla API Hub catalog") and adds scope ("ALL public APIs beyond the top 500"). However, it claims search-keyword filtering, which overlaps with the sibling search_catalog, and never explicitly distinguishes itself from that sibling.

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?

"Use this to explore ALL public APIs beyond the top 500" gives an implied when-to-use, but no when-not and no named alternative. The overlap with search_catalog (both support keyword search) is left unresolved, forcing the agent to infer the boundary.

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

All Zyla API Hub tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?