Delete a file
AI agents call delete-file to permanently remove resources in OpenAI Assistant MCP Server — 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 OpenAI's system. Once deleted, files cannot be recovered. In the context of an AI agent with access to this tool, misuse could result in loss of important data, assistant configurations, or training files. The irreversible nature of file deletion places this in the Destructive category with high severity due to potential data loss impact.
From the tool's definition Tool name 'delete-file' and description 'Delete a file' indicate irreversible removal of data. Deletion is a destructive operation that cannot be undone.
Attacks that exploit this kind of access
Delete a file. It is categorised as a Destructive tool in the OpenAI Assistant MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the OpenAI Assistant MCP Server 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 OpenAI Assistant MCP Server. 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 OpenAI Assistant MCP Server MCP server (snilld-ai/openai-assistant-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 →