Skip to main content
Glama
Sign In

Scrappa

by co.scrappa
OverviewDiscussionsAdmin

Get a YouTube video transcript

youtube_get_transcript
Read-onlyIdempotent

Get the public transcript (captions) of a YouTube video. Accepts a video URL or video id. Returns English when available, otherwise the video language, unless you ask for a language. Returns the language and the full transcript text, cut at 40,000 characters for very long videos. Reads public data only.

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": {
      "video": "<video>"
    },
    "name": "youtube_get_transcript"
  }
}

Input Schema

NameRequiredDescriptionDefault
videoYesYouTube video URL or 11-character video id, e.g. "https://www.youtube.com/watch?v=dQw4w9WgXcQ".
languageNoPreferred transcript language code, e.g. "en" or "de". Default: English, or the video language when there is no English transcript.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / language / description
      Previous value: -"Preferred transcript language code, e.g. \"en\" or \"de\". Default: the video language."New value: +"Preferred transcript language code, e.g. \"en\" or \"de\". Default: English, or the video language when there is no English transcript."
  2. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover readOnly/idempotent/openWorld, and the description adds real value beyond them: truncation at 40,000 characters, the English-then-video-language fallback, and the public-data-only scope. It stops short of describing failure modes (no captions, private/age-restricted videos) or the shape of the returned object.

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?

Four short sentences, front-loaded with the action, then input forms, default behavior, and output limits — every sentence carries distinct information with no redundancy.

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?

With no output schema, the description usefully states what comes back (language plus full transcript text) and the length cap, which is what an agent needs to handle the result. Missing only error/empty-case behavior for videos lacking captions.

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 coverage is 100% and both parameters are documented there, including the same English/video-language default. The description's language sentence restates the schema rather than adding syntax or edge-case detail, so the baseline 3 applies.

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 (get) and resource (public transcript/captions of a YouTube video), with the accepted input form (URL or id) named up front. Sibling tools are unrelated search/review tools, so disambiguation is trivially satisfied.

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 clear context for use: public videos only, URL or id input, and the default language behavior so the agent knows the call works without extra parameters. It does not state what happens when captions are absent or disabled, which is the one missing usage caveat.

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

All Scrappa toolsInspect
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