Borrowing it
Nothing to install: this file belongs to Rajbagus/rabbitorial-capcut-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/Rajbagus/rabbitorial-capcut-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/Rajbagus/rabbitorial-capcut-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/rajbagus/rabbitorial-capcut-mcp/agents-md)<a href="https://agentmods.dev/instructions/rajbagus/rabbitorial-capcut-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/rajbagus/rabbitorial-capcut-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/rajbagus/rabbitorial-capcut-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/rajbagus/rabbitorial-capcut-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 | $0.01368 | $0.01368 |
| Opus 5 | $0.00684 | $0.00684 |
| Sonnet 5 | $0.00274 | $0.00274 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
rabbitorial-capcut-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 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.
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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent setup playbook
This file tells an AI coding agent how to install, register, and verify this
CapCut MCP server end-to-end. Follow it in order. The goal state: the user's
Claude Code (or other MCP client) exposes a capcut server whose tools can
create and edit CapCut drafts that open directly in the CapCut desktop app.
What this is
A local MCP server that drives CapCut by
writing/editing its native draft files. It runs entirely on the user's
machine and makes no outbound network calls for its core editing work.
(Two remote "phone-home" endpoints present in the original upstream project
have been removed — see NOTICE.)
Prerequisites — check these first
- Python 3.10+ on PATH. Check:
python --version(orpython3). - CapCut desktop installed. The server writes drafts into CapCut's projects folder; if CapCut isn't installed, drafts have nowhere to appear.
- An MCP client with a CLI — normally Claude Code (
claude). If theclaudeCLI isn't available, you'll register the server manually (below). - git (only needed if the user hasn't already cloned this repo).
Do not proceed to registration until Python is confirmed ≥ 3.10.
Fast path (preferred)
From the repository root, run:
python install.py
install.py will: create .venv, install dependencies, locate the CapCut
drafts folder for this OS, write a local config.json, smoke-test that the
server imports, and register the server with Claude Code (or print the exact
registration command if the claude CLI is missing).
If install.py completes and prints "Registered as MCP server 'capcut'",
you are done — tell the user to restart their MCP client so the tools load,
then verify (below).
Manual path (if the fast path fails or you prefer explicit steps)
Run these from the repository root. Adjust python/python3 to the platform.
- Create + populate a virtual environment
python -m venv .venv # Windows: .venv\Scripts\python -m pip install --upgrade pip # macOS: .venv/bin/python -m pip install --upgrade pip <venv-python> -m pip install -r requirements.txt -r requirements-mcp.txt
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 · 119 lines · 1,368 tokens per session scan A fa716383b08a
rabbitorial-capcut-mcp AGENTS.md is an instructions file published in the GitHub repository Rajbagus/rabbitorial-capcut-mcp (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,368 tokens to every session, about $0.0068 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).
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.