获取可用的语音音色列表
AI agents call get_available_voices 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 is a simple data retrieval operation that queries and returns a list of available voices for the text-to-speech system. It has no ability to modify state, execute code, delete data, or perform any other operations. The blast radius if misused by an AI agent is negligible.
From the tool's definition Tool name 'get_available_voices' and description indicating it retrieves/lists available voice options ('获取可用的语音音色列表' = 'Get list of available voice timbres/styles'). No side effects, modification, execution, or destruction.
Attacks that exploit this kind of access
获取可用的语音音色列表. 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_available_voices: 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_available_voices 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_available_voices 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_available_voices. 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_available_voices 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 →