获取所有可用的工具列表
AI agents call get_all_available_tools 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 query/list operation that retrieves metadata about available tools. It has no destructive, financial, or code execution impact. It does not modify data. Classification as Read is appropriate; severity is low as enumeration of tool lists poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'get_all_available_tools' and description '获取所有可用的工具列表' (Get list of all available tools) — retrieves/enumerates system capabilities without modification or side effects.
Attacks that exploit this kind of access
获取所有可用的工具列表. 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_all_available_tools: 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_all_available_tools 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_all_available_tools 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_all_available_tools. 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_all_available_tools 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 →