Youtube

Yt Search

yt_search

Read-onlyIdempotent

Search YouTube for videos, channels, or playlists. Returns snippet info including title, description, channel, thumbnails, and publish date.

Input Schema

TableJSON Schema

Name	Required	Description
`type`	No	Resource type to search: "video", "channel", or "playlist" (default: "video")
`order`	No	Sort order: "date", "rating", "relevance", or "viewCount" (default: "relevance")
`query`	Yes	Search term
`_apiKey`	Yes	YouTube Data API v3 key from Google Cloud Console
`channel_id`	No	Filter results to a specific channel ID
`max_results`	No	Number of results to return (default 10, max 50)
`published_after`	No	Filter results published after this ISO 8601 date (e.g. "2024-01-01T00:00:00Z")

Output Schema

TableJSON Schema

Name	Required	Description	Default
`results`	Yes	Array of search result items
`total_results`	Yes	Total number of search results available

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedMay 8, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "results": {
+      "description": "Array of search result items",
+      "items": {
+        "properties": {
+          "channel_id": {
+            "description": "Channel ID",
+            "type": "string"
+          },
+          "channel_title": {
+            "description": "Channel title",
+            "type": "string"
+          },
+          "description": {
+            "description": "Resource description",
+            "type": "string"
+          },
+          "id": {
+            "description": "Video, channel, or playlist ID",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "kind": {
+            "description": "Resource kind (youtube#video, youtube#channel, etc.)",
+            "type": "string"
+          },
+          "published_at": {
+            "description": "ISO 8601 publish date",
+            "type": "string"
+          },
+          "thumbnail": {
+            "description": "Default thumbnail URL",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "title": {
+            "description": "Resource title",
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "kind",
+          "title",
+          "description",
+          "channel_title",
+          "channel_id",
+          "published_at",
+          "thumbnail"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "total_results": {
+      "description": "Total number of search results available",
+      "type": "number"
+    }
+  },
+  "required": [
+    "total_results",
+    "results"
+  ],
+  "type": "object"
+}

Changed1 schema field changedMay 6, 2026

addedInput schema / examples

Added value: +[
+  {
+    "_apiKey": "your-youtube-api-key",
+    "query": "machine learning tutorial"
+  },
+  {
+    "_apiKey": "your-youtube-api-key",
+    "max_results": 20,
+    "order": "viewCount",
+    "published_after": "2024-01-01T00:00:00Z",
+    "query": "Python programming",
+    "type": "video"
+  }
+]

First observedApr 22, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds useful context about returned snippet fields, which is sufficient beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no wasted words. The action and key result are front-loaded.

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?

Given the schema coverage, examples, output schema, and rich annotations, the description is complete enough for an agent to understand the tool's behavior and use it correctly.

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?

All 7 parameters are fully described in the input schema (100% coverage). The description does not add significant meaning beyond what the schema and examples provide.

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 clearly states the tool searches YouTube for videos, channels, or playlists, and lists the returned snippet info. It is distinct from sibling tools like yt_channel_details or yt_video_details.

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?

The description implies search functionality but does not explicitly guide when to use this tool vs sibling tools like yt_channel_details. No when-not-to-use or alternatives are mentioned.

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

All Youtube 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.