Deletes a file from the sandbox environment.
AI agents call delete_file to permanently remove resources in FFmpeg MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes files without recovery options. Although scoped to a sandbox, deletion is irreversible and matches the Destructive category definition. Severity is high because an AI agent could be tricked into deleting important files (e.g., input media, processed outputs, or configuration), disrupting workflows. The sandbox isolation prevents impact beyond the sandbox, preventing critical severity.
From the tool's definition Tool name 'delete_file' with description 'Deletes a file from the sandbox environment' explicitly performs irreversible deletion of data.
Attacks that exploit this kind of access
Deletes a file from the sandbox environment. It is categorised as a Destructive tool in the FFmpeg MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the FFmpeg MCP Server MCP server in PolicyLayer and add a rule for delete_file: 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 Server. Nothing to install.
delete_file is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_file 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 delete_file. 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.
delete_file is provided by the FFmpeg MCP Server MCP server (radzevich/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 →