压缩单个图片文件
AI agents use compress_image to create or update resources in FFmpeg MCP Tool — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FFmpeg MCP Tool environment.
Image compression is a reversible modification operation — the original file can be recovered or a new compressed version created without permanent data loss. This fits Write (creates or modifies data reversibly) rather than Destructive.
From the tool's definition Tool performs image compression ("compress_image"), which modifies file data. Description states "压缩单个图片文件" (compress a single image file). This creates a new or modified version of the image file.
Attacks that exploit this kind of access
压缩单个图片文件. It is categorised as a Write tool in the FFmpeg MCP Tool MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the FFmpeg MCP Tool MCP server in PolicyLayer and add a rule for compress_image: 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.
compress_image is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the compress_image 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 compress_image. 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.
compress_image 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 →