根据索引获取语音音色
AI agents call get_voice_by_index_tool 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 retrieves voice characteristics or metadata by index. It is a read-only query operation with no side effects, no code execution, no data modification, and no destructive capabilities. The blast radius of misuse is minimal—an agent might retrieve unintended voice data but cannot modify systems, execute commands, or cause irreversible changes.
From the tool's definition Tool name contains 'get' and description translates to 'Get voice timbre/characteristics by index' — a retrieval operation with no modification or execution of external processes.
Attacks that exploit this kind of access
根据索引获取语音音色. 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 get_voice_by_index_tool: 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.
get_voice_by_index_tool 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 get_voice_by_index_tool 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 get_voice_by_index_tool. 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.
get_voice_by_index_tool 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 →