Skip to main content
Glama
Sign In

RoxyAPI Docs MCP Server (keyless, for coding agents)

by com.roxyapi
OverviewDiscussionsAdmin

search_docs

Read-only

Search the RoxyAPI knowledge base and get back ranked documentation snippets, each with a source URL. It covers API endpoints with their request and response fields, SDK usage for TypeScript, Python, PHP, C#, Go, Rust, and Dart, the WordPress plugin, authentication and API keys, UI components, and step by step integration guides. Call this first whenever you need to integrate RoxyAPI into an app: to find which endpoint or SDK method to use, what parameters a call takes, how to authenticate, or how to wire a feature end to end. Pass the user question verbatim as query. If the first results miss, rephrase once and retry.

Input Schema

NameRequiredDescriptionDefault
limitNoMax hits to return. Default 10, capped at 25.
queryYesUser question or keywords. Free text. The whole question works better than guessed keywords.
compactNoSet true for the same data in a compact shape: arrays of same-shaped objects arrive columnar as {"__cols":[names],"__rows":[[values]]}. Lossless, typically 40 to 52 percent fewer tokens.

Output Schema

NameRequiredDescriptionDefault
hitsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / properties / hits / items / properties / source_type / enum
      Previous value: -[
-  "guide",
-  "agents",
-  "template",
-  "openapi"
-]New value: +[
+  "guide",
+  "agents",
+  "template",
+  "openapi",
+  "component"
+]
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "hits": {
+      "items": {
+        "properties": {
+          "rank": {
+            "type": "number"
+          },
+          "snippet": {
+            "type": "string"
+          },
+          "source_type": {
+            "enum": [
+              "guide",
+              "agents",
+              "template",
+              "openapi"
+            ],
+            "type": "string"
+          },
+          "title": {
+            "type": "string"
+          },
+          "url": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "title",
+          "url",
+          "snippet",
+          "source_type",
+          "rank"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "hits"
+  ],
+  "type": "object"
+}
  3. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "query": "how do I authenticate an API request"
+  }
+]
    • changedInput schema / properties / compact / description
      Previous value: -"Set true to receive the exact same data in a token-optimized shape that is cheaper for you to read: whitespace is stripped and every array of same-shaped objects is encoded columnar as {\"__cols\":[field names],\"__rows\":[[values]]}, so each field name is sent once instead of once per row. Fully lossless (no field or value is dropped or changed) and typically 40 to 52 percent fewer tokens on large results. Prefer true whenever token or inference cost matters. Default false returns standard indented JSON."New value: +"Set true for the same data in a compact shape: arrays of same-shaped objects arrive columnar as {\"__cols\":[names],\"__rows\":[[values]]}. Lossless, typically 40 to 52 percent fewer tokens."
  4. Changed1 schema field changed
    • changedInput schema / properties / compact / description
      Previous value: -"Return the same data in a token-optimized compact shape (minified, with same-shaped arrays encoded columnar) to reduce LLM token cost. Lossless: no fields are dropped. Default false."New value: +"Set true to receive the exact same data in a token-optimized shape that is cheaper for you to read: whitespace is stripped and every array of same-shaped objects is encoded columnar as {\"__cols\":[field names],\"__rows\":[[values]]}, so each field name is sent once instead of once per row. Fully lossless (no field or value is dropped or changed) and typically 40 to 52 percent fewer tokens on large results. Prefer true whenever token or inference cost matters. Default false returns standard indented JSON."
  5. Changed1 schema field changed
    • addedInput schema / properties / compact
      Added value: +{
+  "default": false,
+  "description": "Return the same data in a token-optimized compact shape (minified, with same-shaped arrays encoded columnar) to reduce LLM token cost. Lossless: no fields are dropped. Default false.",
+  "type": "boolean"
+}
  6. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful behavior beyond that: results are ranked and carry source URLs, and a documented retry-on-miss policy. It stops short of describing pagination or result-count behavior (partly covered by the `limit` schema field).

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?

The purpose and call-first directive are front-loaded, and the retry advice closes usefully. The long enumeration of SDK languages and feature areas is the only slightly listy stretch, though it legitimately tells the agent what queries will match.

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 annotations covering safety, an output schema covering return shape, and full parameter coverage, the description only needs to establish purpose, when to call, and query phrasing, all of which it does. Nothing an agent needs to invoke this search correctly is missing.

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 description coverage is 100%, so the schema already defines all three parameters, including the compact-format token savings and the limit cap. The description reinforces the `query` semantic ("Pass the user question verbatim as `query`"), which largely duplicates the schema's "whole question works better than guessed keywords", so it adds only marginal meaning. Baseline 3 is appropriate.

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 ("Search the RoxyAPI knowledge base") plus the return shape ("ranked documentation snippets, each with a source URL"). It then enumerates the covered content domains (endpoints, SDK languages, WordPress plugin, auth, UI components, integration guides), so an agent knows exactly what corpus is being queried without opening the schema.

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?

Gives an explicit trigger ("Call this first whenever you need to integrate RoxyAPI into an app") and concrete intents that select it: picking an endpoint or SDK method, finding parameters, authenticating, wiring a feature end to end. It also adds a recovery policy ("If the first results miss, rephrase once and retry"), leaving little to inference; with no sibling tools, exclusions are not applicable.

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

All RoxyAPI Docs MCP Server (keyless, for coding agents) toolsInspect
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