What is yt-mcp-remote CLAUDE.md?

Project instructions for yt-mcp-remote, a remote server that provides YouTube video transcripts to connected AI tools. It explains the Python setup, OAuth login, server startup, and the server's main files.

Setting up dependencies, starting the HTTP server, understanding its transcript tools, and working with authentication or server instructions.

It gives a coding agent the project-specific information needed to install, run, and modify the server correctly.

How ShawhinT/yt-mcp-remote configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ShawhinT/yt-mcp-remote. 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/ShawhinT/yt-mcp-remote/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ShawhinT/yt-mcp-remote

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/shawhint/yt-mcp-remote/claude-md/github.svg)](https://agentmods.dev/instructions/shawhint/yt-mcp-remote/claude-md)

Your own site

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

Per session 972 This file is loaded in full into every session.

When invoked 972 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	$0.00972	$0.00972
Opus 5.5	$0.00389	$0.00389
Sonnet 5.5	$0.00194	$0.00194
Haiku 4.5	$0.00097	$0.00097

Measured 2mo ago against content hash 5fe723862fd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

yt-mcp-remote 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.

CLAUDE.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 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.

Project Overview

This is a YouTube MCP (Model Context Protocol) remote server that provides tools for extracting and working with YouTube video transcripts. It runs as an HTTP-accessible MCP server using FastMCP with OAuth authentication and is designed to be consumed by MCP clients remotely (including ChatGPT).

Development Setup

This project uses uv for Python dependency management. The project requires Python >=3.13.

# Install dependencies
uv sync

# Run the server
uv run python main.py

The server runs on 0.0.0.0 using streamable-http transport.

Architecture

Core Components

main.py - Single-file server implementation containing:

MCP server initialization with FastMCP
Auth0 OAuth authentication configuration
Server instructions loaded from prompts/server_instructions.md
Two MCP tools exposed to clients

utils/auth.py - Auth0 token verification module:

Auth0TokenVerifier: Verifies JWT tokens using Auth0's JWKS
Validates token signature, issuer, audience, and expiration
Caches JWKS to minimize Auth0 API calls
Returns AccessToken with user info and scopes

Authentication

The server uses OAuth 2.0 with Auth0:

JWT tokens verified using RS256 algorithm (configurable via AUTH0_ALGORITHMS)
Tokens fetched from Auth0's JWKS endpoint (https://{domain}/.well-known/jwks.json)
Required environment variables (in .env):
- AUTH0_DOMAIN: Auth0 tenant domain
- AUTH0_AUDIENCE: API identifier from Auth0 dashboard
- RESOURCE_SERVER_URL: Server's public URL (for OAuth flow)
- AUTH0_ALGORITHMS (optional): JWT algorithm, defaults to "RS256"

The server requires the following OAuth scopes:

openid
profile
email
address
phone
offline_access

Proxy Configuration

The server requires proxy credentials to fetch YouTube transcripts:

Uses youtube-transcript-api with proxy support via GenericProxyConfig
Required environment variables:
- PROXY_USERNAME: Proxy authentication username
- PROXY_PASSWORD: Proxy authentication password
- PROXY_URL: Proxy server URL (format: hostname:port)

Read the full file on GitHub · 106 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.

2mo ago First seen · 106 lines · 972 tokens per session scan A 5fe723862fd7

Subscribe to this mod's changes

yt-mcp-remote CLAUDE.md is an instructions file published in the GitHub repository ShawhinT/yt-mcp-remote (10 stars, last pushed 1y ago), licensed Apache-2.0. It adds 972 tokens to every session, about $0.0039 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.

yt-mcp-remote CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
yt-mcp-remote CLAUDE.mdShawhinT/yt-mcp-remote	Instructions file	10	1y ago	Apache-2.0	A	972	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

yt-mcp-remote: Instructions file for Claude Code