Soft-delete a neuron. It can be recovered later.
AI agents call ons_delete to permanently remove resources in Open Neural Substrate — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although the tool permits recovery ('can be recovered later'), the primary action is destructive—it removes data from a persistent knowledge graph. This falls under the Destructive category because the deletion action itself is the core function, and recovery requires additional steps.
From the tool's definition Tool is named 'ons_delete' and described as 'Soft-delete a neuron.' The action removes data from the knowledge graph, even though recovery is possible. Deletion is irreversible from the user's perspective until explicit recovery is initiated.
Attacks that exploit this kind of access
Soft-delete a neuron. It can be recovered later. It is categorised as a Destructive tool in the Open Neural Substrate MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Open Neural Substrate MCP server in PolicyLayer and add a rule for ons_delete: 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 Open Neural Substrate. Nothing to install.
ons_delete 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 ons_delete 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 ons_delete. 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.
ons_delete is provided by the Open Neural Substrate MCP server (pedroknigge/open-neural-substrate). 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 →