Skip to main content
Glama

Read the captions of a YouTube video as text

youtube_transcript
Read-only

A YouTube video's captions as plain text and timestamped segments, with the video's title, channel, duration, views, publish date, chapters and the list of caption languages. Accepts watch, youtu.be, shorts, embed and live links or the 11-character id; pick a language with lang (default English, else the first track). Auto-generated captions contain recognition errors. A video without captions is a 404 and not charged. Price: $0.01 per successful call, paid with x402 (USDC on Base, Solana and 10 more networks); failed calls are not charged.

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": "youtube_transcript"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesA YouTube link (watch, youtu.be, shorts, embed or live), or the 11-character video id
langNoCaption language code, e.g. en, de or pt-BR (optional)

Output Schema

NameRequiredDescriptionDefault
noteNo
videoNo
sourceNo
checkedAtNo
transcriptNo
availableLanguagesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed20 schema fields changed
    • removedInput schema / properties / id
      Removed value: -{
      -  "description": "The 11-character video id, instead of url",
      -  "type": "string"
      -}
    • changedInput schema / properties / lang / description
      Previous value: -"Preferred caption language code, e.g. en, de or pt-BR; default the video's original language"New value: +"Caption language code, e.g. en, de or pt-BR (optional)"
    • changedInput schema / properties / url / description
      Previous value: -"A YouTube link (watch, youtu.be, shorts or embed), or leave it out and use id"New value: +"A YouTube link (watch, youtu.be, shorts, embed or live), or the 11-character video id"
    • addedInput schema / required
      Added value: +[
      +  "url"
      +]
    • addedOutput schema / properties / availableLanguages
      Added value: +{}
    • removedOutput schema / properties / channel
      Removed value: -{}
    • removedOutput schema / properties / durationSeconds
      Removed value: -{}
    • removedOutput schema / properties / method
      Removed value: -{}
    • removedOutput schema / properties / segmentCount
      Removed value: -{}
    • removedOutput schema / properties / segments
      Removed value: -{}
    • removedOutput schema / properties / segmentsTruncated
      Removed value: -{}
    • removedOutput schema / properties / text
      Removed value: -{}
    • removedOutput schema / properties / textChars
      Removed value: -{}
    • removedOutput schema / properties / title
      Removed value: -{}
    • removedOutput schema / properties / track
      Removed value: -{}
    • removedOutput schema / properties / tracks
      Removed value: -{}
    • addedOutput schema / properties / transcript
      Added value: +{}
    • removedOutput schema / properties / truncated
      Removed value: -{}
    • addedOutput schema / properties / video
      Added value: +{}
    • removedOutput schema / properties / videoId
      Removed value: -{}
  2. Added

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the readOnly/openWorld annotations: states a caption-less video returns 404 and is not charged, discloses pricing ($0.01 per successful call via x402 USDC on Base/Solana and 10+ networks), that failures are free, and the default-language fallback behavior. That is unusually complete behavioral context for a paid read 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?

Front-loads the return payload, then inputs, then caveats and pricing; each sentence carries distinct information. The final pricing sentence is dense and the network enumeration is slightly padded, but nothing is clearly wasted.

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?

Output schema exists, so return-value detail is not required, yet the description still summarizes the payload. Payment model, error semantics, language defaults, and accepted inputs are all covered, leaving no material gap for a 2-parameter tool.

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 real meaning beyond the schema: accepted URL formats are enumerated and lang is given default semantics (English, else first track). The 11-char id acceptance is also useful beyond the schema's brief note.

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?

Names a specific verb+resource: reads a YouTube video's captions as plain text and timestamped segments, plus enumerated metadata returned (title, channel, duration, views, date, chapters, caption languages). An agent can distinguish this from generic transcript tools because the input formats and outputs are spelled out precisely.

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?

Gives concrete context: accepts watch/youtu.be/shorts/embed/live links or the 11-char id, defaults lang to English else the first track, and warns auto-generated captions contain errors. It stops short of naming when to prefer a sibling transcript tool, so no explicit exclusions.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources