RoxyAPI Docs MCP Server (keyless, for coding agents)

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#, and Go, 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

TableJSON Schema

Name	Required	Description
`limit`	No	Max hits to return. Default 10, capped at 25.
`query`	Yes	User question or keywords. Free text. The whole question works better than guessed keywords.
`compact`	No	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.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`hits`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 22, 2026

changedOutput schema / properties / hits / items / properties / source_type / enum

Previous value: -[
-  "guide",
-  "agents",
-  "template",
-  "openapi"
-]New value: +[
+  "guide",
+  "agents",
+  "template",
+  "openapi",
+  "component"
+]

Changed1 schema field changedSep 20, 2026

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"
+}

Changed2 schema fields changedAug 17, 2026

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."

Changed1 schema field changedJul 22, 2026

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."

Changed1 schema field changedJul 22, 2026

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"
+}

First observedJul 8, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations declare readOnlyHint=true and destructiveHint=false, so the safety profile is already known. The description goes beyond annotations by explaining ranking with source URLs, the coverage breadth, and the recommendation to pass the user question verbatim and retry rephrased. This gives an agent a clear mental model of 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?

The description is somewhat long but front-loads the core purpose and output in the first sentence. The enumerated coverage list and usage guidance are relevant, though the list of SDK languages could be considered slightly verbose; still, every sentence contributes to call decisions.

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 an output schema present, the return format is already specified. The description covers why to use the tool, what it searches, how to pass the query, and how to recover from poor results. All three parameters are fully documented in the schema, so nothing essential is missing for correct invocation.

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 description coverage is 100%, with good parameter descriptions for query, limit, and compact. The description adds operational guidance on top: 'Pass the user question verbatim as `query`' and the retry instruction, which is useful. Since the schema already carries the syntactic meaning, a 4 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?

The description uses a specific verb ('Search'), identifies a clear resource ('RoxyAPI knowledge base'), and states the output ('ranked documentation snippets, each with a source URL'). It also enumerates the content areas covered (API endpoints, SDKs, WordPress plugin, auth, UI components, integration guides), so an agent knows exactly what this tool searches though.

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 instructs to 'Call this first whenever you need to integrate RoxyAPI into an app' and lists concrete trigger scenarios: finding endpoints or SDK methods, parameter details, authentication, and feature wiring. It also gives a retry strategy ('If the first results miss, rephrase once and retry'), which is actionable guidance.

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) 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.

Resources

Need Help?