Discard a pending proposal without committing it. Deletes the staging row;
AI agents call memory_reject to permanently remove resources in Loom — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool explicitly deletes a staging row and discards a pending proposal. This is an irreversible deletion of data (the staging/pending proposal is permanently removed). While the blast radius is limited to a single staging record rather than committed memory, the action is non-reversible, placing it in the Destructive category.
From the tool's definition Discard a pending proposal without committing it. Deletes the staging row
Attacks that exploit this kind of access
Discard a pending proposal without committing it. Deletes the staging row;. It is categorised as a Destructive tool in the Loom MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Loom MCP server in PolicyLayer and add a rule for memory_reject: 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 Loom. Nothing to install.
memory_reject 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_reject 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_reject. 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_reject is provided by the Loom MCP server (jbarket/loom). 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 →