AI agents call project_delete_file to permanently remove resources in 8th Wall MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes files from the project directory. File deletion cannot be undone and represents irreversible data loss. While the blast radius is limited to the project workspace (not system-wide), deletion of critical project files (configuration, source code, assets) could render the AR experience non-functional or unrecoverable.
From the tool's definition Tool name contains 'delete' and description states 'Delete a file under PROJECT_ROOT', which is an irreversible operation that removes data.
Documented attack patterns abuse exactly the kind of access project_delete_file gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and 8th Wall MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for project_delete_file:
{
"version": "1",
"default": "deny",
"hide": [
"project_delete_file"
]
}project_delete_file disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete a file under PROJECT_ROOT. It is categorised as a Destructive tool in the 8th Wall MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the 8th Wall MCP Server MCP server in PolicyLayer and add a rule for project_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 8th Wall MCP Server. Nothing to install.
project_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 project_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 project_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.
project_delete_file is provided by the 8th Wall MCP Server MCP server (superdwayne/8thwallmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from 8th Wall MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
64 8th Wall MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.