Borrowing it
Nothing to install: this file belongs to u2n4/video-url-analyzer-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/u2n4/video-url-analyzer-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/u2n4/video-url-analyzer-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/u2n4/video-url-analyzer-mcp/agents-md)<a href="https://agentmods.dev/instructions/u2n4/video-url-analyzer-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/u2n4/video-url-analyzer-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.01926 | $0.01926 |
| Opus 5 | $0.00963 | $0.00963 |
| Sonnet 5 | $0.00385 | $0.00385 |
| Haiku 4.5 | $0.00193 | $0.00193 |
Grade A, and why
video-url-analyzer-mcp AGENTS.md scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Image downloads use `_download_media_url`: urllib (system DNS, 3 Copies of this mod
1 near-identical copy found in the catalogue:
- video-url-analyzer-mcp CLAUDE.md — 100% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Analyzer MCP Server
Project Purpose
MCP server for video/photo analysis using Google's Gemini API. Supports YouTube (direct, no download), TikTok (videos + photo slideshows), and Instagram (Reels, video posts, and photo carousels). Downloaded media is uploaded to the Gemini Files API and analyzed with full visual (and, for videos, audio) coverage.
Architecture
server.py: Main MCP server with 17 v1.4 tools: the original analysis/transcript/Q&A/tutorial tools, structured moment/segment tools, saved video context tools, local evidence asset tools, and cache tools.- Pipelines:
- YouTube: Direct analysis via
Part.from_uri()(no download). - TikTok/Instagram video: Fast-path API/scrape → yt-dlp fallback → upload to Gemini Files API → analyze → cleanup.
- TikTok/Instagram photo carousel: Scrape image URLs from page/API → download each image → upload ALL images to Gemini → analyze as a single carousel with ordered slides → cleanup.
- YouTube: Direct analysis via
_download_video(url)returnslist[str](one path for a video, many for a carousel)._analyze_downloadedhandles both transparently.- YouTube frame/clip extraction has a fast local path using
yt-dlp -gstream URLs + ffmpeg. Ifsource.mp4is missing but a saved context has the original YouTube URL, asset tools can still extract frames/clips. - FastMCP for MCP protocol (stdio transport).
- google-genai SDK for Gemini API interaction.
Media download strategy
- TikTok photo posts: tikwm.com API returns
data.images[]of image URLs. - Instagram photo posts: page HTML is scraped; the
carousel_media/edge_sidecar_to_childrenJSON block is isolated to avoid picking up thumbnails of suggested/related posts. Falls back to whole-page scan if the block isn't present. Hard cap at 20 unique images. - Image downloads use
_download_media_url: urllib (system DNS, 3 retries) → curl_cffi impersonate fallback. urllib-first was added because curl_cffi's bundled resolver intermittently fails to resolve some*.fna.fbcdn.netCDN shards on Windows while system DNS works. - All temp files deleted in a
finallyblock; uploaded Gemini files are also deleted after the analysis call returns.
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.
- 8d ago First seen · 159 lines · 1,926 tokens per session scan A d3d1007ed2f5
video-url-analyzer-mcp AGENTS.md is an instructions file published in the GitHub repository u2n4/video-url-analyzer-mcp (3 stars, last pushed 2mo ago), licensed MIT. It adds 1,926 tokens to every session, about $0.0096 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.