Borrowing it
Nothing to install: this file belongs to miracleweasel/katto-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/miracleweasel/katto-mcp/main/GEMINI.mdgit clone --depth 1 https://github.com/miracleweasel/katto-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/miracleweasel/katto-mcp/gemini-md)<a href="https://agentmods.dev/instructions/miracleweasel/katto-mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/miracleweasel/katto-mcp/gemini-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/miracleweasel/katto-mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/miracleweasel/katto-mcp/gemini-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 | $0.00423 | $0.00423 |
| Opus 5.5 | $0.00169 | $0.00169 |
| Sonnet 5.5 | $0.00085 | $0.00085 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
katto-mcp GEMINI.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 17d 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
Katto (video clipping MCP server)
Katto turns a long video into scored, captioned 9:16 short clips in its cloud. Nothing renders locally.
First run
The server is hosted at https://mcp.katto.tech/mcp and uses OAuth. If tool calls fail with an auth error, tell the user to run /mcp auth katto and sign in to their Katto account in the browser. tools/list works before sign-in.
Core flow
katto_create_clip_job({ url })with a YouTube, Twitch, Kick, Vimeo, Zoom, Google Drive, Dropbox, Loom… link, orkatto_upload_videofirst for a local file. This spends 1 video of the user's monthly quota (2 on Free, 10 on Solo, 25 on Creator), so confirm before starting several jobs, and passidempotency_keyif you might retry.- Poll
katto_get_job({ id })every 30–60 s untilstatusiscompleted(a long video takes several minutes). katto_get_clips({ id })returns the MP4 + SRT urls, titles and a 0–100 score per clip. Present the best-scored ones first.
Follow-ups that don't spend a video
katto_more_clips, katto_create_clip (any time range), katto_rerender_clip (layout / caption style), katto_adjust_clip (trim / extend), katto_retitle_clip (AI titles have a monthly allowance), katto_translate_captions and katto_dub_clip (Creator plan). Check remaining quota with katto_get_usage.
Publishing
katto_publish_clip posts to the social accounts the user connected in Katto. Always get the user's explicit go-ahead first (which clip, which platform, the caption).
Full tool reference: https://katto.tech/mcp/tools
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.
- 17d ago First seen · 20 lines · 423 tokens per session scan A ef62fc4ca154
katto-mcp GEMINI.md is an instructions file published in the GitHub repository miracleweasel/katto-mcp (4 stars, last pushed 2d ago), licensed MIT. It adds 423 tokens to every session, about $0.0017 per session on Opus 5.5. 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 2026-10-20.
katto-mcp GEMINI.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| katto-mcp GEMINI.mdmiracleweasel/katto-mcp | Instructions file | 4 | 2d ago | MIT | A | 423 | Gemini CLI |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |