获取媒体文件信息
AI agents call get_media_info to retrieve information from FFmpeg MCP Tool without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and returns information about media files (dimensions, codec, duration, bitrate, etc.) without side effects. It performs no destructive, write, or execution operations. The low severity reflects that misuse poses minimal risk—an agent could only gather information about media files, not manipulate them or trigger external operations.
From the tool's definition Tool name 'get_media_info' and description 'retrieve media file information' indicate a query operation that returns metadata without modifying or executing actions on the underlying files.
Attacks that exploit this kind of access
获取媒体文件信息. It is categorised as a Read tool in the FFmpeg MCP Tool MCP Server, which means it retrieves data without modifying state.
Register the FFmpeg MCP Tool MCP server in PolicyLayer and add a rule for get_media_info: 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 MCP Tool. Nothing to install.
get_media_info 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_media_info 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_media_info. 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_media_info is provided by the FFmpeg MCP Tool MCP server (lbjwt/ffmpeg-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 →