清理字幕文本
AI agents use clean_subtitle_text to create or update resources in Auto Video Generator — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Auto Video Generator environment.
The tool appears to process/clean subtitle text, which likely involves modifying or sanitizing text data. This is a Write operation as it transforms/modifies text content. However, the description is minimal and provides little detail, so confidence is moderate. It could also be a pure Read/transform operation with no persistent side effects, but 'cleaning' implies modification, placing it in Write.
From the tool's definition Tool name: 'clean_subtitle_text'; description: '清理字幕文本' (meaning 'clean subtitle text' in Chinese)
Attacks that exploit this kind of access
清理字幕文本. It is categorised as a Write tool in the Auto Video Generator MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Auto Video Generator MCP server in PolicyLayer and add a rule for clean_subtitle_text: 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 Auto Video Generator. Nothing to install.
clean_subtitle_text 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 clean_subtitle_text 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 clean_subtitle_text. 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.
clean_subtitle_text is provided by the Auto Video Generator MCP server (zgmurder/auto_video_generator-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →