Delete a file at the given path.
AI agents call delete_file to permanently remove resources in Modular MCP Server & Client — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently deletes files, which is a destructive operation that cannot be reversed. This is classified as Destructive rather than Write because the action is irreversible. Severity is high because unintended file deletion can cause significant system damage or data loss, though the blast radius depends on file permissions and which files an agent might target.
From the tool's definition Tool name is 'delete_file' and description states 'Delete a file at the given path.' This irreversibly removes data without undo capability.
Attacks that exploit this kind of access
Delete a file at the given path. It is categorised as a Destructive tool in the Modular MCP Server & Client MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Modular MCP Server & Client 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 Modular MCP Server & Client. 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 Modular MCP Server & Client MCP server (jackmichaud/modular-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 →