TranscriptYT

Get YouTube transcript

get_transcript

Read-only

Fetch the transcript of a public YouTube video. Accepts a full URL or an 11-character video ID. Defaults to Markdown (title + text), which is the most compact format for reading or summarizing. Use json for timestamped segments, srt/vtt for subtitle files. Costs 1 credit on success; videos without captions are AI-transcribed at 1 credit per started minute.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "get_transcript"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes	YouTube URL or video ID
`mode`	No	auto: captions, AI-transcribed audio if there are none. captions: never AI. ai: always transcribe the audio (1 credit per started minute)	auto
`format`	No	Output format	md
`search`	No	Only return lines containing this text
`end_time`	No	Only return the part before this second
`language`	No	Preferred caption language (BCP-47, e.g. en, es, pt-BR)
`start_time`	No	Only return the part from this second on
`timestamps`	No	Prefix lines with timestamps (text/md)
`translate_to`	No	Translate the transcript into this language
`original_language`	No	Prefer the spoken language's captions over English

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 13, 2026

addedInput schema / properties / mode

Added value: +{
+  "default": "auto",
+  "description": "auto: captions, AI-transcribed audio if there are none. captions: never AI. ai: always transcribe the audio (1 credit per started minute)",
+  "enum": [
+    "auto",
+    "captions",
+    "ai"
+  ],
+  "type": "string"
+}

Changed4 schema fields changedOct 3, 2026

addedInput schema / properties / end_time

Added value: +{
+  "description": "Only return the part before this second",
+  "type": "number"
+}

addedInput schema / properties / original_language

Added value: +{
+  "description": "Prefer the spoken language's captions over English",
+  "type": "boolean"
+}

addedInput schema / properties / search

Added value: +{
+  "description": "Only return lines containing this text",
+  "type": "string"
+}

addedInput schema / properties / start_time

Added value: +{
+  "description": "Only return the part from this second on",
+  "type": "number"
+}

First observedOct 2, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already establish read-only, open-world, non-destructive behavior, and the description adds important cost and fallback details: 1 credit on success and AI transcription at 1 credit per started minute when captions are absent. It does not cover failure behavior or rate limits, but it adds meaningful context beyond the 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?

The description is short, front-loaded with the core action and accepted inputs, then moves efficiently through format choice and cost. Every sentence contributes useful selection or behavioral information.

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?

For a 10-parameter tool with no output schema, the description covers the essential context: public-video scope, URL/ID input, default format, format alternatives, and credit costs including AI transcription. It is nearly complete, though it could briefly mention error or no-caption edge cases beyond the cost note.

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 the baseline is 3, but the description adds rationale beyond the schema: Markdown is presented as the most compact format, json as timestamped segments, and srt/vtt as subtitle files. It also ties AI transcription cost to the no-caption case, which clarifies mode behavior.

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?

The description states a specific verb and resource: fetch the transcript of a public YouTube video, with accepted input forms. It is clear enough to distinguish from generic search or summarization siblings, but it does not explicitly contrast itself with summarize_video.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives useful selection guidance for output formats: Markdown for compact reading/summarizing, json for timestamped segments, and srt/vtt for subtitle files. It does not explicitly say when to prefer this tool over siblings like summarize_video, but the format guidance is clear.

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

All TranscriptYT 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?