根据素材路径(TUTORIAL_DIR) 和 草稿目录(draft_folder) 生成剪映草稿.
AI agents use generate_jianying to create or update resources in Dy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dy environment.
This tool creates or modifies video editing project drafts in a specified folder path. While the action is reversible (drafts can be deleted), it does write new files and metadata to the system. The context of a Douyin automation server suggests this is part of a workflow to create video content programmatically.
From the tool's definition Tool generates drafts (generates 剪映 Jianyingcraft files) into a specified directory (draft_folder), which creates new data artifacts. The verb '生成' (generate/create) indicates content creation.
Documented attack patterns abuse exactly the kind of access generate_jianying gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Dy, and nothing reaches the server without passing your rules. This is the rule we recommend for generate_jianying:
{
"version": "1",
"default": "deny",
"tools": {
"generate_jianying": {
"limits": [
{
"counter": "generate_jianying_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}generate_jianying stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
根据素材路径(TUTORIAL_DIR) 和 草稿目录(draft_folder) 生成剪映草稿. It is categorised as a Write tool in the Dy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Dy MCP server in PolicyLayer and add a rule for generate_jianying: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Dy. Nothing to install.
generate_jianying is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the generate_jianying rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for generate_jianying. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
generate_jianying is provided by the Dy MCP server (vipcong816/dy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Dy, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Dy tools catalogued and risk-classified — across an index of 43,000+ MCP servers.