Skip to main content
Glama
Social Fetch MCP

Social Fetch MCP

Official

Get YouTube video transcript

youtube_video_transcript_get
Read-onlyIdempotent

Fetch a YouTube video's transcript by URL or 11-character ID, optionally choosing a language or restricting results to the original spoken language.

Instructions

Get the transcript for a YouTube video by URL. Requires url. Pass the video link or 11-character id in url, e.g. {"url":"dQw4w9WgXcQ"}; there is no videoId field.

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>",
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "youtube_video_transcript_get"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesRequired. Link to the YouTube video whose transcript should be returned.
contextYesDescribe the user's underlying goal in one sentence, not the tool you are calling.
languageNoOptional language code to prefer when multiple transcripts exist: a two- or three-letter code (`en`, `es`), optionally with a region or script (`en-US`, `pt-BR`, `zh-Hans`). See `availableLanguages` for the codes a video offers.
llm_modelYesThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess.
originalAudioNoWhen `true`, only return captions in the video's original spoken language, and ignore `language`. If the original language can't be identified or has no captions, `transcript` is `null`. Default: `false`.
conversation_idNoEcho the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

B3.2/5.0
Behavior2/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is fully covered. The description adds no behavioral context beyond that: nothing about failure modes when captions are absent, whether the call can be slow, or what the response contains. It is a pure invocation note, not a behavioral one.

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 short sentences, the action first and the URL-format constraint second, with a concrete example. Every clause carries information an agent needs at call time; nothing is padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With six parameters (three required, including meta-parameters like `context` and `llm_model`) and no output schema, the description covers only `url`. The schema documents everything else thoroughly, so this is survivable, but the description never hints what comes back (transcript text, available languages) or that a null result is a normal outcome when captions are missing.

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 would be 3, but the description genuinely adds meaning by clarifying that `url` accepts either a full link or a bare 11-character id and by explicitly warning 'there is no videoId field' — a real error-prevention detail found nowhere in the schema. It still says nothing about `context`, `llm_model`, `language`, or `conversation_id`, so it isn't a full replacement for the schema.

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?

States a specific verb and resource ('Get the transcript for a YouTube video'), which cleanly separates it from the dailymotion/rumble/tiktok transcript siblings by platform. It does not, however, distinguish itself from non-transcript YouTube siblings like youtube_video_get, leaving the agent to infer that difference from the name alone.

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

Usage Guidelines2/5

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

The description explains how to call the tool (pass a link or 11-character id) but never says when to prefer it over siblings such as youtube_video_get or the other platform transcript tools. No exclusions, no prerequisites, and no mention of the language/originalAudio trade-off that governs which transcript you get.

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

Deploy Server

Other Tools