Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/brian-huanggg/youtube-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/mcp/brian-huanggg/youtube-mcp/youtube-watch-mcp)<a href="https://agentmods.dev/mcp/brian-huanggg/youtube-mcp/youtube-watch-mcp"><img src="https://agentmods.dev/badge/mcp/brian-huanggg/youtube-mcp/youtube-watch-mcp/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/mcp/brian-huanggg/youtube-mcp/youtube-watch-mcp"><img src="https://agentmods.dev/badge/mcp/brian-huanggg/youtube-mcp/youtube-watch-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
youtube-watch-mcp 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 12d 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-watch-mcp": { "command": "uvx", "args": [ "youtube-watch-mcp" ] } }
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.
- 12d ago First seen · 8 lines scan A 72d6e568ae0f
youtube-watch-mcp is an MCP server published in the GitHub repository brian-huanggg/youtube-mcp (0 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 mcp servers, from other repositories
youtube-studio
MCP server "youtube-studio" as configured in hygef-v4/youtube-studio-mcp. Runs locally from the git+https://github.com/hygef-v4/youtube-studio-mcp.git Python package. Needs 2 environment variables to run.
mcp-searxng
MCP server for SearXNG — privacy-respecting web search with pagination, URL reading. Runs locally from the mcp-searxng npm package. Needs 3 environment variables to run.
mcp-youtube-transcript
MCP server "mcp-youtube-transcript" as configured in jkawamoto/mcp-youtube-transcript. Launched with https://github.com/jkawamoto/mcp-youtube-transcript/releases/download/v0.7.1/mcp.
bitrise-mcp
MCP Server for Bitrise, enabling app management, build operations, artifact management, and more. Remote server at mcp.bitrise.io.
glif
Generate images, video, and audio with Glif's media-generation agent. Remote server at glif.app.
transcriptor-mcp
MCP server "transcriptor-mcp" as configured in samson-art/transcriptor-mcp. Runs in Docker (docker.io/artsamsonov/transcriptor-mcp:1.2.4).