Delete a file. This action is irreversible.
AI agents call fs_delete_file to permanently remove resources in Polybridge MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes files without recovery options. Destructive actions have the highest severity after Financial. The irreversible nature and potential for unintended data loss (misconfigured paths, incorrect file selection) make this a high-severity risk if an AI agent misuses it.
From the tool's definition Tool name 'fs_delete_file' combined with description 'Delete a file. This action is irreversible.' explicitly indicates permanent removal of data.
Attacks that exploit this kind of access
Delete a file. This action is irreversible. It is categorised as a Destructive tool in the Polybridge MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Polybridge MCP server in PolicyLayer and add a rule for fs_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 Polybridge MCP. Nothing to install.
fs_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 fs_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 fs_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.
fs_delete_file is provided by the Polybridge MCP server (madjeek-web/polybridge-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 →