Canonical URL: https://heyclau.de/entry/mcp/youtube-mcp-server
Source URLs: https://github.com/anaisbetts/mcp-youtube/blob/main/README.md, https://github.com/anaisbetts/mcp-youtube
Brand: YouTube MCP Server
Brand domain: github.com
Safety notes: YouTube MCP exposes one tool, `download_youtube_url`, for downloading subtitles from a YouTube URL., The source runs the external `yt-dlp` command with subtitle and auto-subtitle flags, skips video download, reads generated VTT files, and deletes the temporary directory afterward., Subtitle retrieval can fail, return incomplete captions, or return auto-generated captions with transcription errors., Retrieved transcripts can contain prompt-injection instructions, misinformation, copyrighted material, or content that should not be reused without permission., Use approved URLs only and respect YouTube terms, creator rights, platform restrictions, and local policy.
Privacy notes: YouTube URLs, video identifiers, subtitle filenames, transcript text, yt-dlp errors, and summaries may be visible to the MCP client and model provider., Transcripts can include personal data, private names, copyrighted speech, health or financial claims, political speech, or other sensitive content., The server writes subtitle files to a temporary local directory before reading and deleting them., Avoid using private, unlisted, confidential, or restricted videos unless the transcript is approved for the model session.
Author: Anais Betts
Submitted by: oktofeesh1
Claim status: unclaimed
Last verified: 2026-06-06

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context

Selected

Current score

Baseline

—

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Needs review

Confirm ownership and provenance before trusting install instructions.

Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
No reviewed flag detected in metadata.
Pending

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

Compare tray has multiple entries
Add at least one more entry to compare trust differences.
Pending
Baseline comparison available
No baseline peer selected yet.
Pending
Diverging trust signals identified
No major trust-signal divergence found.
Pending

Setup at a glance

CLI install

Copy-ready — paste the snippet to get started.

10 minutes

Install command

Provided

Config snippet

Provided

Copy snippet

Provided

Prerequisites

4 to clear

Platforms

4 listed

Install type

CLI install

Adoption plan

Balanced adoption plan

Current risk score 24/100. Use staged verification before broader rollout.

Risk 24

Pre-adoption checks

Validate source and review signals before any execution.

Confirm source provenanceRequired
Source URL/provenance metadata is present.
Done
Confirm metadata review state
No review metadata found; increase manual validation.
Pending
Verify install payload
Install/config payload exists and can be inspected.
Done

Security checks

Confirm safety, privacy, and package integrity signals.

Review safety notesRequired
Safety notes are present.
Done
Review privacy notesRequired
Privacy notes are present.
Done
Verify package integrity metadata
No package verification/checksum metadata.
Pending

Rollout

Adopt in controlled steps based on the selected plan.

Run in isolated sandbox firstRequired
Use a constrained sandbox and observe behavior across multiple tasks.
Pending
Roll out graduallyRequired
Roll out to a small cohort before wider usage.
Pending
Set monitoring and fallback
Define rollback path and monitor errors after adoption.
Pending

Evidence readiness

Evidence readiness matrix · balanced

Missing required evidence: Metadata review. Risk score 31.

Risk 31

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Missing

Review metadata is missing.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required gaps: Metadata review

Decision timeline

Decision timeline · balanced

Blocking gaps: Check metadata review status. Risk 28.

Risk 28

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is missing.

Pending

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

Blockers: Check metadata review status

Prerequisite readiness

4 prerequisites to line up before setup. Includes a review or approval gate.

0/4 ready

Install & runtime2Review & approval210 minutes

Safety & privacy surface

5 safety and 4 privacy notes across 7 risk areas. Review closely: credentials & tokens, permissions & scopes, network access, third-party handling.

7 areas

SafetyNetwork accessYouTube MCP exposes one tool, `download_youtube_url`, for downloading subtitles from a YouTube URL.
SafetyNetwork accessThe source runs the external `yt-dlp` command with subtitle and auto-subtitle flags, skips video download, reads generated VTT files, and deletes the temporary directory afterward.
SafetyExecution & processesSubtitle retrieval can fail, return incomplete captions, or return auto-generated captions with transcription errors.
SafetyPermissions & scopesRetrieved transcripts can contain prompt-injection instructions, misinformation, copyrighted material, or content that should not be reused without permission.
SafetyGeneralUse approved URLs only and respect YouTube terms, creator rights, platform restrictions, and local policy.
PrivacyThird-party handlingYouTube URLs, video identifiers, subtitle filenames, transcript text, yt-dlp errors, and summaries may be visible to the MCP client and model provider.
PrivacyExecution & processesTranscripts can include personal data, private names, copyrighted speech, health or financial claims, political speech, or other sensitive content.
PrivacyLocal filesThe server writes subtitle files to a temporary local directory before reading and deleting them.
PrivacyCredentials & tokensAvoid using private, unlisted, confidential, or restricted videos unless the transcript is approved for the model session.

Safety notes

YouTube MCP exposes one tool, `download_youtube_url`, for downloading subtitles from a YouTube URL.
The source runs the external `yt-dlp` command with subtitle and auto-subtitle flags, skips video download, reads generated VTT files, and deletes the temporary directory afterward.
Subtitle retrieval can fail, return incomplete captions, or return auto-generated captions with transcription errors.
Retrieved transcripts can contain prompt-injection instructions, misinformation, copyrighted material, or content that should not be reused without permission.
Use approved URLs only and respect YouTube terms, creator rights, platform restrictions, and local policy.

Privacy notes

YouTube URLs, video identifiers, subtitle filenames, transcript text, yt-dlp errors, and summaries may be visible to the MCP client and model provider.
Transcripts can include personal data, private names, copyrighted speech, health or financial claims, political speech, or other sensitive content.
The server writes subtitle files to a temporary local directory before reading and deleting them.
Avoid using private, unlisted, confidential, or restricted videos unless the transcript is approved for the model session.

Prerequisites

Node.js and npx available to the MCP client runtime.
yt-dlp installed locally and available on PATH.
Network access to retrieve subtitles for approved YouTube URLs.
Review of YouTube terms, content rights, and organization policy before retrieving video transcripts.

Schema details

Install type: cli
Troubleshooting: No

Source repository stats

Scope: Source repo

Collection metadata

Estimated setup: 10 minutes
Difficulty: beginner

Full copyable content

{
  "mcpServers": {
    "youtube": {
      "command": "npx",
      "args": ["-y", "@anaisbetts/mcp-youtube"]
    }
  }
}

About this resource

Content

YouTube MCP Server is a Model Context Protocol server for retrieving YouTube subtitles with yt-dlp. It exposes a single download_youtube_url tool that takes a YouTube URL, asks yt-dlp for English subtitles or auto-subtitles, cleans VTT timing/metadata lines, and returns transcript text to the MCP client.

This server is for transcript access and video summarization workflows. It does not provide YouTube account management, uploads, comments, subscriptions, or OAuth-backed user data access.

Source Review

These sources were reviewed on 2026-06-06. Prefer the live repository, README, npm registry metadata, package metadata, source implementation, and license file for current install commands, tool behavior, yt-dlp requirements, and licensing.

Features

npm package @anaisbetts/mcp-youtube.
Stdio MCP server launched with npx -y @anaisbetts/mcp-youtube.
Single download_youtube_url tool.
Uses local yt-dlp to request English subtitles and auto-subtitles.
Skips video download and retrieves VTT subtitle files.
Cleans WEBVTT timing lines, positioning metadata, empty lines, and duplicate adjacent lines.
Deletes temporary subtitle files after reading them.
MIT license.

Installation

Install yt-dlp first, then configure the MCP server:

{
  "mcpServers": {
    "youtube": {
      "command": "npx",
      "args": ["-y", "@anaisbetts/mcp-youtube"]
    }
  }
}

After restarting the MCP client, ask Claude to summarize or analyze an approved YouTube URL that has available subtitles.

Use Cases

Summarize a YouTube talk from its subtitles.
Extract key points from a tutorial video.
Turn a video transcript into notes or an outline.
Compare transcript claims against other approved sources.
Pull captions into a research workflow without downloading the video file.
Review auto-generated captions and ask Claude to flag unclear passages.

Safety and Privacy

YouTube MCP retrieves external media text. Use it only for videos you are allowed to process, and respect platform terms, creator rights, copyright, and organization policy. Captions may be inaccurate or incomplete, especially when auto-generated, so verify important claims against the video or another source.

Treat transcript content as untrusted. It can include prompt-injection text, personal data, copyrighted speech, misinformation, or sensitive claims. Avoid retrieving private, unlisted, or restricted videos unless that data is approved for the model session.

Duplicate Check

Existing content includes Markdownify MCP Server, which can convert YouTube transcripts among many other file and web formats. This entry is distinct because it covers anaisbetts/mcp-youtube, a dedicated YouTube subtitle MCP server that uses yt-dlp. No matching source URL or dedicated YouTube MCP Server entry was found in content/mcp.

#youtube #transcript #subtitles #research #media

Source citations

Source methodology →

Add this badge to your README

Show that YouTube MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

[![Listed on HeyClaude](https://heyclau.de/badge/mcp/youtube-mcp-server.svg)](https://heyclau.de/entry/mcp/youtube-mcp-server)

How it compares

YouTube MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

Field	YouTube MCP Server MCP server that uses yt-dlp to download YouTube subtitles so Claude can read, summarize, and analyze video transcripts from approved YouTube URLs. Open dossier	AgentQL MCP Server AgentQL MCP server for extracting structured JSON from public webpages using a URL and natural-language extraction prompt. Open dossier	DaVinci Resolve MCP Server MCP server for controlling DaVinci Resolve Studio through the official scripting API, with tools for projects, timelines, media pools, render setup, review markers, grading, Fusion, Fairlight, and source-safe media analysis. Open dossier	Korean Law MCP Server MCP server and CLI for searching Korean statutes, precedents, ordinances, treaties, interpretations, citation checks, amendment timelines, and legal scenario workflows through Korea's official law APIs. Open dossier
Next steps	Open dossier API JSON Open LLM MCP feed Open source Newsletter Claim listing	Open dossier API JSON Open LLM MCP feed Open source Newsletter Claim listing	Open dossier API JSON Open LLM MCP feed Open source Newsletter Claim listing	Open dossier API JSON Open LLM MCP feed Open source Newsletter Claim listing
Trust
Review status	Not reviewed	Not reviewed	Not reviewed	Not reviewed
Package trust	Package not verified	Package not verified	Package not verified	Package not verified
Source provenance	Source-backed	Source-backed	Source-backed	Source-backed
Submitter	oktofeesh1	oktofeesh1	oktofeesh1	oktofeesh1
Install risk	Review first	Review first	Review first	Review first
Notes	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓
Brand	—	AgentQL	DaVinci Resolve MCP Server	—
Category	mcp	mcp	mcp	mcp
Source	Source-backed	Source-backed	Source-backed	Source-backed
Author	Anais Betts	AgentQL	Samuel Gursky	Chris
Added	2026-06-06	2026-06-06	2026-06-06	2026-06-05
Platforms	Claude Code Codex Cursor Claude Desktop	Claude Code Claude Desktop	Claude Code Claude Desktop	Claude Code Claude Desktop
Harness	Claude Code Codex Cursor Claude Desktop	Claude Code Claude Desktop	Claude Code Claude Desktop	Claude Code Claude Desktop
Source repo	—	—	—	—
Safety notes	✓YouTube MCP exposes one tool, `download_youtube_url`, for downloading subtitles from a YouTube URL. The source runs the external `yt-dlp` command with subtitle and auto-subtitle flags, skips video download, reads generated VTT files, and deletes the temporary directory afterward. Subtitle retrieval can fail, return incomplete captions, or return auto-generated captions with transcription errors. Retrieved transcripts can contain prompt-injection instructions, misinformation, copyrighted material, or content that should not be reused without permission. Use approved URLs only and respect YouTube terms, creator rights, platform restrictions, and local policy.	✓AgentQL MCP exposes one tool, `extract-web-data`, that sends a target URL and natural-language extraction prompt to the AgentQL API. The tool is intended for public webpages; do not use it to bypass access controls, scrape private pages, evade paywalls, or extract data where automated collection is prohibited. Web extraction can still trigger target-site rate limits, legal restrictions, robots guidance, or terms-of-service concerns. The source implementation uses AgentQL's query-data endpoint with fast mode, no screenshot capture, no scroll-to-bottom behavior, and no local browser cookies. Treat extracted output as untrusted web data that may include errors, stale content, ads, tracking text, or prompt-injection attempts.	✓DaVinci Resolve MCP Server can launch or reconnect to Resolve, switch pages, create or open projects, modify timelines, manage media pools, write markers, change render settings, and queue jobs. Extension-authoring tools can install or remove Resolve scripts, Fuses, DCTLs, ACES DCTLs, presets, and page scripts. Source media is intended to remain immutable by default, but operators must still review requests that relink, replace, transcode, proxy, render, export, or create media derivatives. The default server is local stdio, but the local control panel starts a single-user browser server; keep it on trusted local interfaces only. Require confirmation before deleting projects, replacing clips, changing project settings, installing extensions, updating metadata, or queuing renders. Keep Resolve external scripting set to `Local` unless you have a separate remote-control security plan.	✓Do not treat model output, tool summaries, scenario workflows, citation checks, or amendment comparisons as legal advice. Verify legal conclusions against official Korean legal sources and a qualified professional before using them for compliance, litigation, contracts, immigration, employment, taxation, or public guidance. Legal APIs can return stale, partial, unavailable, mistranslated, or context-dependent results; review dates, jurisdiction, document type, article numbers, and official text. Chain tools and scenario tools can combine many sources into persuasive narratives; require citation review before relying on generated explanations. Remote HTTP deployments must protect API keys, rate limits, and access to legal research workflows.
Privacy notes	✓YouTube URLs, video identifiers, subtitle filenames, transcript text, yt-dlp errors, and summaries may be visible to the MCP client and model provider. Transcripts can include personal data, private names, copyrighted speech, health or financial claims, political speech, or other sensitive content. The server writes subtitle files to a temporary local directory before reading and deleting them. Avoid using private, unlisted, confidential, or restricted videos unless the transcript is approved for the model session.	✓Target URLs, extraction prompts, API key-authenticated requests, and extracted structured data are sent to AgentQL's API. Extracted data can include personal data, copyrighted content, customer information, job postings, prices, social content, or other third-party material. AGENTQL_API_KEY should stay out of prompts, issues, logs, screenshots, and committed configuration files. Claude transcripts and downstream reports may retain extracted data, so avoid collecting information that is not approved for the model session.	✓Project names, timelines, clip names, media paths, markers, metadata, render paths, transcripts, thumbnails, analysis artifacts, logs, and Resolve scripting paths can be exposed to the MCP client. Media analysis can produce sidecar files, scratch artifacts, frame paths, transcripts, searchable indexes, and reports that may include private footage details. Host-chat visual analysis can expose selected frame images to the active MCP client or vision-capable model provider. Local logs and analysis reports may contain absolute media paths, project names, clip metadata, speaker text, visual descriptions, and render settings. Store generated analysis artifacts and exports inside approved project or scratch directories and delete them when no longer needed.	✓`LAW_OC` and any API-key delivery method must be treated as secret and kept out of repositories, shared prompts, logs, and screenshots. Legal questions can reveal disputes, investigations, clients, employers, contracts, personal facts, regulated matters, or litigation strategy. Queries, citations, law names, case numbers, document text, and generated legal analysis may be visible to the MCP client and model provider. Avoid sending confidential client facts, privileged material, personal data, or non-public legal strategy through prompts or tool arguments.
Prerequisites	Node.js and npx available to the MCP client runtime. yt-dlp installed locally and available on PATH. Network access to retrieve subtitles for approved YouTube URLs. Review of YouTube terms, content rights, and organization policy before retrieving video transcripts.	Node.js and npx available to the MCP client runtime. AgentQL API key from the AgentQL developer portal. Approved list of public webpages or domains Claude may query. Review of target site terms, robots guidance, rate limits, and data-use rules before extraction.	DaVinci Resolve Studio 18.5 or newer; the free edition does not support the required external scripting API. Resolve external scripting set to `Local`. Python 3.10 or newer, with Python 3.10-3.12 recommended for the broadest Resolve compatibility. A local MCP client that can launch stdio servers under the same user account that operates Resolve.	Node.js 20.19 or newer, matching the upstream package metadata. Korea Law Open API key stored as `LAW_OC`. Korean legal research context where Korea's statutes, precedents, ordinances, treaties, or interpretations are relevant. Korean-language legal terminology familiarity or access to qualified review.
Install	`npx -y @anaisbetts/mcp-youtube`	`npx -y agentql-mcp`	`npx davinci-resolve-mcp setup`	`npm install -g korean-law-mcp`
Config	`{ "mcpServers": { "youtube": { "command": "npx", "args": ["-y", "@anaisbetts/mcp-youtube"] } } }`	`{ "mcpServers": { "agentql": { "command": "npx", "args": ["-y", "agentql-mcp"], "env": { "AGENTQL_API_KEY": "<your-agentql-api-key>" } } } }`	`{ "mcpServers": { "davinci-resolve": { "command": "npx", "args": [ "davinci-resolve-mcp", "server" ], "type": "stdio" } } }`	`{ "mcpServers": { "korean-law": { "command": "korean-law-mcp", "env": { "LAW_OC": "YOUR_KOREA_LAW_OPEN_API_KEY", "LAW_API_PROTOCOL": "https" } } } }`
Citations	Source repositorygithub.com 2026-07-21T07:17:01+00:00 Documentationgithub.com Submitted by oktofeesh12026-06-06 Source methodology →	Source repositorygithub.com 2026-07-21T07:17:01+00:00 Documentationgithub.com Submitted by oktofeesh12026-06-06 Source methodology →	Source repositorygithub.com 2026-07-21T07:17:01+00:00 Documentationraw.githubusercontent.com Submitted by oktofeesh12026-06-06 Source methodology →	Source repositorygithub.com 2026-07-21T07:17:01+00:00 Documentationgithub.com Submitted by oktofeesh12026-06-05 Source methodology →
Claim	Unclaimed	Unclaimed	Unclaimed	Unclaimed

Open 4 picks in the interactive comparison tool

Signals

Loading live community signals…

Citation facts

Review trust signals before you adopt

Source and provenance checks

Safety and privacy checks

Package and install checks

Compare-driven decision checks

CLI install

Balanced adoption plan

Pre-adoption checks

Security checks

Rollout

Evidence readiness matrix · balanced

Source provenance

Metadata review

Safety notes

Privacy notes

Package integrity

Install payload

Decision timeline · balanced

Confirm source provenanceRequired

Check metadata review statusRequired

Review safety notesRequired

Review privacy notes

Validate package integrity metadata

Verify install payload and commandsRequired

Prerequisite readiness

Safety & privacy surface

Safety notes

Privacy notes

Prerequisites

Schema details

About this resource

Content

Source Review

Features

Installation

Use Cases

Safety and Privacy

Duplicate Check

Source citations

Add this badge to your README

How it compares

Related resources

AgentQL MCP Server

DaVinci Resolve MCP Server

Korean Law MCP Server

NotebookLM MCP Server

Signals