Borrowing it
Nothing to install: this file belongs to kevinten-ai/mcp-media-toolkit. 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/kevinten-ai/mcp-media-toolkit/main/CLAUDE.mdgit clone --depth 1 https://github.com/kevinten-ai/mcp-media-toolkitWrote 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/kevinten-ai/mcp-media-toolkit/claude-md)<a href="https://agentmods.dev/instructions/kevinten-ai/mcp-media-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/kevinten-ai/mcp-media-toolkit/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.
<a href="https://agentmods.dev/instructions/kevinten-ai/mcp-media-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/kevinten-ai/mcp-media-toolkit/claude-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 | $0.00415 | $0.00415 |
| Opus 5 | $0.00208 | $0.00208 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
mcp-media-toolkit 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 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.
What it actually says
CLAUDE.md — mcp-media-toolkit
Project Overview
MCP server for local image processing — background removal, stock media search, resize, format conversion, and collage creation. All tools are free and work locally (except Pexels search which uses a free API).
Architecture
- Entry:
src/media_toolkit/__init__.py→server.main()via asyncio - Core:
src/media_toolkit/server.py— all logic in one file - Libraries: Pillow (resize, convert, collage), rembg (background removal), httpx (Pexels API)
Key Design Decisions
- All tools save output to
IMAGE_OUTPUT_DIR(default:./output) with timestamped filenames - rembg model (~170MB) downloads automatically on first use — no manual setup needed
output_pathis optional on every tool — auto-generated if omitted- Custom outputs never overwrite inputs or existing files and must use the format's matching extension
- Resource bounds: resize dimensions up to 8192px; collages up to 50 images, 20 columns, and 512px spacing
- Collage canvases are capped at 40 million pixels; inline MCP previews are omitted above 5 MiB while saved files remain available
- SVG→PNG conversion uses cairosvg if available, otherwise returns an error with install instructions
- Pexels search requires
PEXELS_API_KEYenv var (free tier, no cost)
Development
uv sync # install deps
uv run media-toolkit # run server
Common Pitfalls
- First call to
remove_backgroundis slow (~30s) because rembg downloads the U2Net model - JPEG does not support transparency —
convert_formatauto-composites RGBA onto white background - Pexels API has rate limits (200 req/hour on free tier) — no auth = immediate error with helpful message
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 · 36 lines · 415 tokens per session scan A 8d584f3055ed
mcp-media-toolkit CLAUDE.md is an instructions file published in the GitHub repository kevinten-ai/mcp-media-toolkit (0 stars, last pushed 1mo ago), licensed MIT. It adds 415 tokens to every session, about $0.0021 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 2026-08-31.
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).
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.
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.