Delete a document (soft delete - can be restored)
AI agents call docs_delete_document to permanently remove resources in Docs MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool deletes a document, which is a destructive operation. While the description notes it is a soft delete (restorable), the blast radius is still high as an AI agent misusing this tool could delete important documents.
From the tool's definition 'Delete a document' — even though described as 'soft delete - can be restored', the primary action is deletion and it is categorized as Destructive due to the potential for data loss if restoration is not performed
Attacks that exploit this kind of access
Delete a document (soft delete - can be restored). It is categorised as a Destructive tool in the Docs MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Docs MCP Server MCP server in PolicyLayer and add a rule for docs_delete_document: 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 Docs MCP Server. Nothing to install.
docs_delete_document 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 docs_delete_document 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 docs_delete_document. 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.
docs_delete_document is provided by the Docs MCP Server MCP server (nic01asfr/docs-mcp-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 →