YouTube MCP Server

Youtube Get Transcript

youtube_get_transcript

Retrieve a YouTube video's plain-text transcript by video ID, with optional timestamps and pagination, without using YouTube Data API quota.

Instructions

Fetch a YouTube video's transcript as plain text.

Returns the caption text for one 11-character video ID, with the language that was actually used, whether it is auto-generated, and next_cursor.

Timestamps are OFF by default because each [mm:ss] marker costs tokens; when include_timestamps is true a marker is inserted wherever the caption minute changes (a word-level auto-generated track gets far fewer markers than segments).

Long transcripts are truncated at the server's RESPONSE_LIMIT and cut on caption boundaries: read next_cursor and call again with it to get the following page — next_cursor: null (and truncated: false) means you have the whole thing. Each page repeats the time anchor of its first segment.

Costs no YouTube Data API quota: transcripts are scraped from YouTube's internal caption endpoint, not the Data API. They are cached forever, so a repeat call is free. Failures are expected and specific — captions may be disabled, absent in the requested languages, or the IP may be blocked (transient). Age-restricted videos cannot be read.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`cursor`	No
`video_id`	Yes
`languages`	No
`include_timestamps`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`text`	Yes
`language`	Yes
`video_id`	Yes
`truncated`	Yes
`next_cursor`	Yes
`is_generated`	Yes
`language_code`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 4, 2026

TDQS

A4.3/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so richly: no Data API quota, scraped from an internal endpoint, cached forever, server-side truncation at RESPONSE_LIMIT with caption-boundary cuts, first-segment time anchor repeated per page, and named failure modes (captions disabled, missing languages, blocked IP, age-restricted).

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?

Purpose is front-loaded in the first sentence, and the remaining paragraphs are dense and each earns its place (timestamps, pagination, cost, failures). It runs long, but there is little filler; slightly more compression would help.

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?

Even though an output schema exists and would cover return fields, the description still explains next_cursor, truncated, language, and auto-generated flags, plus the truncation/pagination loop. For a tool with a non-trivial paginated return and several failure modes, nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate, and it does for all four params: video_id is an 11-character ID, include_timestamps defaults off and controls [mm:ss] marker insertion density, cursor drives page-to-page continuation, and languages is surfaced through the 'absent in the requested languages' failure mode.

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 ('Fetch a YouTube video's transcript as plain text') and immediately scopes it to one 11-character video ID. It implicitly separates itself from youtube_get_timestamped_transcript via the 'timestamps OFF by default' framing, but never names that sibling explicitly, so the differentiation is left to inference.

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?

Gives strong operational context — pagination via next_cursor, free repeat calls, expected failure modes — but never states when to pick this tool over the timestamped, language-listing, or in-transcript-search siblings. Usage is implied rather than routed.

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

Deploy Server