UNRELATE UNLINK DISCONNECT - Remove a relationship between two memories. Keywords: unrelate, unlink, disconnect, detach, unbind, separate
AI agents call memory_unrelate to permanently remove resources in MCP AI Memory — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool removes/deletes a relationship between two memories. Removing a relationship is a destructive action — it irreversibly severs a link that may not be easily reconstructed, especially in a vector/graph-based memory system. While it doesn't delete the memories themselves, the relationship metadata is deleted, which qualifies as Destructive rather than Write.
From the tool's definition UNRELATE UNLINK DISCONNECT - Remove a relationship between two memories. Keywords: unrelate, unlink, disconnect, detach, unbind, separate
Documented attack patterns abuse exactly the kind of access memory_unrelate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP AI Memory, and nothing reaches the server without passing your rules. This is the rule we recommend for memory_unrelate:
{
"version": "1",
"default": "deny",
"hide": [
"memory_unrelate"
]
} memory_unrelate disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
UNRELATE UNLINK DISCONNECT - Remove a relationship between two memories. Keywords: unrelate, unlink, disconnect, detach, unbind, separate. It is categorised as a Destructive tool in the MCP AI Memory MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP AI Memory MCP server in PolicyLayer and add a rule for memory_unrelate: 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 MCP AI Memory. Nothing to install.
memory_unrelate 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 memory_unrelate 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 memory_unrelate. 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.
memory_unrelate is provided by the MCP AI Memory MCP server (scanadi/mcp-ai-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 17 MCP AI Memory tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
17 MCP AI Memory tools catalogued and risk-classified — across an index of 42,500+ MCP servers.