智能分割文本为字幕片段
AI agents call split_text_for_subtitles to retrieve information from Auto Video Generator without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to perform text processing — splitting input text into subtitle segments. It is a pure transformation/computation operation with no persistent side effects, no file writes, and no external system calls indicated. It reads/processes input text and returns segmented output, classifying it as Read (data transformation with no side effects).
From the tool's definition 'split_text_for_subtitles' and description '智能分割文本为字幕片段' (intelligently split text into subtitle segments)
Attacks that exploit this kind of access
智能分割文本为字幕片段. It is categorised as a Read tool in the Auto Video Generator MCP Server, which means it retrieves data without modifying state.
Register the Auto Video Generator MCP server in PolicyLayer and add a rule for split_text_for_subtitles: 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.
split_text_for_subtitles is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the split_text_for_subtitles 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 split_text_for_subtitles. 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.
split_text_for_subtitles 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 →