检查系统支持的硬件加速选项
AI agents call check_hardware_acceleration to retrieve information from FFmpeg Python MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a system query to enumerate supported hardware acceleration options. It retrieves data about system capabilities with no side effects, state changes, or external execution triggered. This is purely informational and falls under the Read category as a low-severity, non-privileged diagnostic check.
From the tool's definition Tool name 'check_hardware_acceleration' and description indicate querying/checking system capabilities ('检查系统支持的硬件加速选项' = 'Check system-supported hardware acceleration options').
Attacks that exploit this kind of access
检查系统支持的硬件加速选项. It is categorised as a Read tool in the FFmpeg Python MCP Server MCP Server, which means it retrieves data without modifying state.
Register the FFmpeg Python MCP Server MCP server in PolicyLayer and add a rule for check_hardware_acceleration: 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 FFmpeg Python MCP Server. Nothing to install.
check_hardware_acceleration 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 check_hardware_acceleration 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 check_hardware_acceleration. 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.
check_hardware_acceleration is provided by the FFmpeg Python MCP Server MCP server (mabh111111/ffmpeg_python_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 →