Delete a file or directory from a remote WebDAV server
AI agents call webdav_delete_remote_item to permanently remove resources in WebDAV MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of files or directories cannot be undone and represents permanent data loss. This is a classic destructive operation with high blast radius if an AI agent misuses the tool (e.g., deleting critical system files or user data).
From the tool's definition Tool name 'webdav_delete_remote_item' explicitly indicates deletion of files or directories from a remote WebDAV server. Description states 'Delete a file or directory from a remote WebDAV server' — irreversible data destruction.
Attacks that exploit this kind of access
Delete a file or directory from a remote WebDAV server. It is categorised as a Destructive tool in the WebDAV MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the WebDAV MCP Server MCP server in PolicyLayer and add a rule for webdav_delete_remote_item: 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 WebDAV MCP Server. Nothing to install.
webdav_delete_remote_item 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 webdav_delete_remote_item 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 webdav_delete_remote_item. 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.
webdav_delete_remote_item is provided by the WebDAV MCP Server MCP server (masx200/mcp-webdav-server). 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 →