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/Diterex/youtube-research-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/diterex/youtube-research-mcp/yt-research-mcp)<a href="https://agentmods.dev/mcp/diterex/youtube-research-mcp/yt-research-mcp"><img src="https://agentmods.dev/badge/mcp/diterex/youtube-research-mcp/yt-research-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/diterex/youtube-research-mcp/yt-research-mcp"><img src="https://agentmods.dev/badge/mcp/diterex/youtube-research-mcp/yt-research-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
yt-research-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 11d 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
{ "yt-research-mcp": { "command": "uvx", "args": [ "yt-research-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.
- 11d ago First seen · 8 lines scan A 3dbb4c2725c7
yt-research-mcp is an MCP server published in the GitHub repository Diterex/youtube-research-mcp (0 stars, last pushed 9d 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
yt-dlp
Production-grade MCP server that lets LLM agents inspect, plan, download, and postprocess media URLs with yt-dlp, including YouTube and youtu.be links. 28 typed tools, managed output roots, safe argv execution, full yt-dlp option catalog. Runs locally from the yt-dlp-mcp-server npm package.
youtube-shorts-agent
Agent-first YouTube Shorts uploader: dry-run validation, OAuth checks, synthetic-media metadata. Runs locally from the youtube-shorts-agent npm package. Needs 3 environment variables to run.
appsgolem-mcp
Cut clips from YouTube videos in any format and get a direct download URL. Runs locally from the appsgolem-mcp npm package. Needs 2 environment variables to run.
tube-bridge
Tube Bridge — YouTube MCP server for AI agents. 17 tools: search, transcripts, frames, semantic corpus, comments. Zero keys + optional API v3. Runs locally from the tube-bridge Python package. Needs 3 environment variables to run.
youtube
YouTube MCP — wraps the YouTube Data API v3 (BYO API key). Remote server at gateway.pipeworx.io.
youtube-analytics-mcp
YouTube Analytics MCP. Runs locally from the youtube-analytics-mcp npm package.