Borrowing it
Nothing to install: this file belongs to yunlinwu/youtube-transcript-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.
curl -O https://raw.githubusercontent.com/yunlinwu/youtube-transcript-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/yunlinwu/youtube-transcript-mcpWrote 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.
[](https://agentmods.dev/instructions/yunlinwu/youtube-transcript-mcp/claude-md)<a href="https://agentmods.dev/instructions/yunlinwu/youtube-transcript-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/yunlinwu/youtube-transcript-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.
<a href="https://agentmods.dev/instructions/yunlinwu/youtube-transcript-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/yunlinwu/youtube-transcript-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00362 | $0.00362 |
| Opus 5.5 | $0.00145 | $0.00145 |
| Sonnet 5.5 | $0.00072 | $0.00072 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
youtube-transcript-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 2mo 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.
What it actually says
YouTube Transcript MCP Server
What this is
An MCP server (Python) that gives Claude access to YouTube video transcripts.
Two tools: get_transcript_tool and search_transcript.
Architecture
server.py — MCP tool definitions (FastMCP), error handling, response formatting
transcript.py — extraction logic: yt-dlp captions → VTT parsing → Segment list
Whisper fallback when captions unavailable (optional dep)
Dev setup
python3 -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]" # core + pytest
pip install -e ".[whisper]" # optional Whisper fallback
Running tests
pytest tests/ -v
Running the server
youtube-transcript-mcp # stdio mode (used by Claude Desktop)
Key decisions
- Captions first, Whisper fallback: captions are fast and free; Whisper requires downloading audio + ~140MB model. Whisper is an optional dependency.
- Tools return
{"error": "..."}on failure instead of raising — Claude gets a useful message it can relay to the user. search_transcriptmerges overlapping context windows so nearby matches don't produce redundant output.- Segments include both raw seconds and human-readable timestamps (
"1:30:05").
Dependencies
mcp[cli]— MCP SDK (FastMCP)yt-dlp— YouTube downloading/metadata/subtitlesopenai-whisper— speech-to-text fallback (optional)ffmpeg— required by Whisper (system install)
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.
- 2mo ago First seen · 45 lines · 362 tokens per session scan A c0da4d32c506
youtube-transcript-mcp CLAUDE.md is an instructions file published in the GitHub repository yunlinwu/youtube-transcript-mcp (1 stars, last pushed 3mo ago), licensed MIT. It adds 362 tokens to every session, about $0.0014 per session on Opus 5.5. 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 2026-08-31.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.