file-manager
AI agents call file-manager to permanently remove resources in IMCP - Insecure Model Context Protocol — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The description is empty, which lowers confidence significantly. However, 'file-manager' tools typically span Read, Write, and Destructive operations (list, read, write, delete files). Given the most-severe-applicable rule, and that file managers commonly include delete/overwrite capabilities, Destructive is selected.
From the tool's definition Tool name 'file-manager' on a server described as 'deliberately vulnerable' with 'critical security weaknesses'
Attacks that exploit this kind of access
file-manager. It is categorised as a Destructive tool in the IMCP - Insecure Model Context Protocol MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the IMCP - Insecure Model Context Protocol MCP server in PolicyLayer and add a rule for file-manager: 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 IMCP - Insecure Model Context Protocol. Nothing to install.
file-manager 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 file-manager 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 file-manager. 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.
file-manager is provided by the IMCP - Insecure Model Context Protocol MCP server (nav33n25/imcp). 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 →