Borrowing it
Nothing to install: this file belongs to bartivs/yt-media-info-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/bartivs/yt-media-info-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/bartivs/yt-media-info-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/bartivs/yt-media-info-mcp/agents-md)<a href="https://agentmods.dev/instructions/bartivs/yt-media-info-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bartivs/yt-media-info-mcp/agents-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/bartivs/yt-media-info-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bartivs/yt-media-info-mcp/agents-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 | $0.02081 | $0.02081 |
| Opus 5 | $0.01040 | $0.01040 |
| Sonnet 5 | $0.00416 | $0.00416 |
| Haiku 4.5 | $0.00208 | $0.00208 |
Grade A, and why
yt-media-info-mcp AGENTS.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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
yt-media-info MCP — Agent Guide
Quick start
npm install
npm start # stdio mode (for Claude Desktop)
ENABLE_SSE=1 npm start # SSE mode (Express on :9423)
npm run dev # nodemon auto-restart
npm run lint # ESLint flat config
Architecture
- Single ESM package (
"type": "module"). Entrypoint:src/index.js. - Wraps the Python yt-dlp library via a persistent FastAPI HTTP service (
yt-dlp-service), not viadocker run --rm. The service imports yt-dlp once at startup and caches extractors. - Two transport modes controlled by
ENABLE_SSEenv var:- stdio (
ENABLE_SSE=0, default): connect viaStdioServerTransport— used by Claude Desktop. - SSE (
ENABLE_SSE=1): Express onYT_MEDIA_INFO_HOST:YT_MEDIA_INFO_PORT(default0.0.0.0:9423). Endpoints:GET /sse,POST /messages,POST /api,GET /health,GET /(cookie upload form),POST /upload-cookies,POST /delete-cookies.
- stdio (
POST /apiis a shortcut that calls the Python service directly for a specific tool (bypasses MCP protocol). Usage:{ "tool": "extract_info", "args": { "url": "..." } }.- Three MCP tools:
extract_info,get_transcript,search_media. - Two MCP prompts:
analyze_video,summarize_transcript. - Optional bearer API key auth (via
YT_MEDIA_INFO_API_KEYenv var) protects HTTP endpoints in SSE mode. stdio mode is unaffected. - Docker Compose deployment: two containers (
yt-dlp-service+yt-media-info-mcp) on a bridge network with healthcheck +depends_on. No host Docker socket mount required.
Key files
| Path | Role |
|---|---|
src/index.js |
Server bootstrap, transport setup, graceful shutdown, direct /api handler, cookie upload routes and helpers |
src/tools/extract-info.js |
extract_info MCP tool (POSTs to Python /info) |
src/tools/get-transcript.js |
get_transcript MCP tool (POSTs to Python /transcript) |
src/tools/search-media.js |
search_media MCP tool (POSTs to Python /search) |
src/schemas/extractInfoSchema.js |
Zod param schema for extract_info |
src/schemas/transcriptSchema.js |
Zod param schema for get_transcript |
src/schemas/searchSchema.js |
Zod param schema for search_media |
src/sseManager.js |
SSE transport lifecycle + progress notifications |
src/prompts/ |
MCP prompt templates (analyze_video, summarize_transcript) |
src/logger.js |
Winston logger (JSON format, colorized console transport) |
service/main.py |
FastAPI application with /health, /info, /transcript, /search endpoints |
service/requirements.txt |
Python dependencies: yt-dlp[default], fastapi, uvicorn[standard] |
compose.yaml |
Three-container Docker Compose with healthcheck + bridge network (plus optional cookie-bot with --profile cookies) |
.env.example |
Default environment configuration (committed; copy to .env and customize) |
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.
- 9d ago First seen · 122 lines · 2,081 tokens per session scan A 7a2a2beb498c
yt-media-info-mcp AGENTS.md is an instructions file published in the GitHub repository bartivs/yt-media-info-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,081 tokens to every session, about $0.0104 per session on Opus 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 2026-09-01.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
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.