DESTRUCTIVE. Permanently delete one file by ID. KB files are unlinked from disk AND removed from the FTS5 index; project reference files only have their index entry removed (the file on disk is left alone so the watcher does not fight your editor). Not idempotent — deleting an unknown ID throws. ...
AI agents call delete_file to permanently remove resources in Kontexta — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes files from disk and indexes, which is an irreversible destructive operation. It cannot be undone and causes data loss. While the blast radius is somewhat constrained by operating only on files within the knowledge base (not arbitrary filesystem access), the permanence of deletion and explicit destructive labeling place this in the Destructive category rather than Write.
From the tool's definition Tool description explicitly states 'DESTRUCTIVE. Permanently delete one file by ID' and 'KB files are unlinked from disk AND removed from the FTS5 index'. The operation is irreversible and cannot be undone.
Attacks that exploit this kind of access
DESTRUCTIVE. Permanently delete one file by ID. KB files are unlinked from disk AND removed from the FTS5 index; project reference files only have their index entry removed (the file on disk is left alone so the watcher does not fight your editor). Not idempotent — deleting an unknown ID throws. No external auth or rate limits. Returns. It is categorised as a Destructive tool in the Kontexta MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Kontexta 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 Kontexta. 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 Kontexta MCP server (safiyu/kontexta). 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 →