What is youtube-mcp CLAUDE.md?

A project guide for Claude Code, an agent that edits software repositories. It explains the YouTube MCP server, its conventions, command-line setup, authentication, and safety rules.

Working on a Python server that connects to YouTube data, analytics, and reporting services. It covers multi-brand-account sign-in, quota tracking, command-line administration, testing, and type checking.

It gives the coding agent repository-specific rules before it changes code, including which commands to use and which YouTube operations must not be exposed.

How sigvardt/youtube-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sigvardt/youtube-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/sigvardt/youtube-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/sigvardt/youtube-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/sigvardt/youtube-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/sigvardt/youtube-mcp/claude-md)

Your own site

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

Per session 2,897 This file is loaded in full into every session.

When invoked 2,897 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	$0.02897	$0.02897
Opus 5.5	$0.01159	$0.01159
Sonnet 5.5	$0.00579	$0.00579
Haiku 4.5	$0.00290	$0.00290

Measured 2mo ago against content hash d56995e86036, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

youtube-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.

CLAUDE.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Agent-facing guide for working on youtube-mcp. Read this before touching the codebase.

If you arrived here looking for "how do I use youtube-mcp as a tool from my agent", you want skills/youtube-mcp/SKILL.md instead. This file is for editing the server itself.

What this repo is

A single Python package, youtube_mcp, that:

Boots a FastMCP server (src/youtube_mcp/server.py).
Registers ~84+ tools across 17 tool modules under src/youtube_mcp/tools/ covering YouTube Data v3, Analytics v2, and Reporting v1.
Manages multi-brand-account OAuth, refresh, and quota tracking.
Exposes a Typer CLI (youtube-mcp serve | auth ... | status | doctor | tools list) so an operator can set up accounts and probe health without writing Python.

Project conventions (non-negotiable)

uv run for everything. Never call python, pip, pytest, mypy, ruff, or pyright directly. The system Python is not the project Python. Always uv run <command>.
mypy --strict is the source of truth. Every module passes --strict. New code must too. # type: ignore requires a same-line justification comment naming the third-party limitation.
ruff check is clean. Config lives in ruff.toml. Rules: E,F,W,I,B,UP,RUF, line length 100, target py311.
pyright runs in CI as a second opinion. Some Google client stubs are partial; the existing # pyright: reportMissingTypeStubs=false block at the top of cli.py is the pattern when you have to suppress.
No # type: ignore shotgun. If you find yourself adding more than one ignore to a new file, stop and re-shape the types.
Pydantic v2 for all model shapes. Every public model uses ConfigDict(extra="forbid"). See types.py for the canon.
from __future__ import annotations at the top of every module. Consistent and matches the existing style.
No print() for production logging. Use FastMCP Context.log inside tools, and the module logger in server.py for boot-time messages.
No emojis, no em dashes, no en dashes in source or docs. This is enforced by review, not lint.
Append to .sisyphus/notepads/youtube-mcp/learnings.md when you discover something non-obvious. Never overwrite.

Read the full file on GitHub · 178 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 · 178 lines · 2,897 tokens per session scan A d56995e86036

Subscribe to this mod's changes

youtube-mcp CLAUDE.md is an instructions file published in the GitHub repository sigvardt/youtube-mcp (1 stars, last pushed 5mo ago), licensed MIT. It adds 2,897 tokens to every session, about $0.0116 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.

youtube-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
youtube-mcp CLAUDE.mdsigvardt/youtube-mcp	Instructions file	1	5mo ago	MIT	A	2,897	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

youtube-mcp: Instructions file for Claude Code