What is yt-dlp-mcp CLAUDE.md?

Repository instructions for yt-dlp-mcp, a server that lets an AI assistant use yt-dlp to search for and download online video or audio and related data.

Use them when changing video, audio, subtitles, search, metadata, comments, or server configuration code.

They make version updates, builds, tests, and changelog entries follow the project's required process.

How kevinwatt/yt-dlp-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kevinwatt/yt-dlp-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/kevinwatt/yt-dlp-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/kevinwatt/yt-dlp-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kevinwatt/yt-dlp-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/kevinwatt/yt-dlp-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/kevinwatt/yt-dlp-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kevinwatt/yt-dlp-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/kevinwatt/yt-dlp-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kevinwatt/yt-dlp-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,070 This file is loaded in full into every session.

When invoked 2,070 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.02070	$0.02070
Opus 5	$0.01035	$0.01035
Sonnet 5	$0.00414	$0.00414
Haiku 4.5	$0.00207	$0.00207

Measured 13d ago against content hash c55550dc8f45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

yt-dlp-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Development Guidelines

Always update CHANGELOG.md when making changes to the codebase
Version updates require TWO files:
1. package.json - line 3: "version": "x.x.x"
2. src/index.mts - line 24: const VERSION = 'x.x.x'

Development Commands

Build and Prepare

npm run prepare  # Compile TypeScript and make binary executable

Testing

npm test  # Run Jest tests with ESM support

Manual Testing

node ./lib/index.mjs  # Start local built MCP server manually

Code Architecture

MCP Server Implementation

This is an MCP (Model Context Protocol) server that integrates with yt-dlp for video/audio downloading. The server:

Entry point: src/index.mts - Main MCP server implementation with tool handlers
Modular design: Each feature lives in src/modules/ (video.ts, audio.ts, subtitle.ts, search.ts, metadata.ts, comments.ts)
Configuration: src/config.ts - Centralized config with environment variable support and validation
Utility functions: src/modules/utils.ts - Shared spawn and cleanup utilities

Tool Architecture

The server exposes 10 MCP tools (all prefixed with ytdlp_ in the protocol layer):

search_videos - YouTube video search
list_subtitle_languages - List available subtitles
download_video_subtitles - Download subtitle files
download_video - Download videos with resolution/trimming options
download_audio - Extract and download audio
download_transcript - Generate clean text transcripts
get_video_metadata - Extract comprehensive video metadata (JSON format)
get_video_metadata_summary - Get human-readable metadata summary
get_video_comments - Extract comments as flat JSON, threaded JSON, or AI-friendly Markdown
get_video_comments_summary - Get human-readable flat or threaded comment summaries

Read the full file on GitHub · 187 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

13d ago First seen · 187 lines · 2,070 tokens per session scan A c55550dc8f45

Subscribe to this mod's changes

yt-dlp-mcp CLAUDE.md is an instructions file published in the GitHub repository kevinwatt/yt-dlp-mcp (278 stars, last pushed 1mo ago), licensed MIT. It adds 2,070 tokens to every session, about $0.0103 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

yt-dlp-mcp: Instructions file for Claude Code