Delete a memory from the brain by its ID.
AI agents call forget to permanently remove resources in Open Brain 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 data without reversibility. While the blast radius is limited to a single user's knowledge base (not financial or system-wide), unintended deletion of important memories/context could significantly impair an AI agent's ability to function correctly or recover important work history. Classified as Destructive rather than Write because deletion cannot be undone without external backups.
From the tool's definition Tool description states 'Delete a memory from the brain by its ID.' The verb 'delete' combined with 'by its ID' indicates irreversible removal of specific data records.
Attacks that exploit this kind of access
Delete a memory from the brain by its ID. It is categorised as a Destructive tool in the Open Brain MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Open Brain MCP Server MCP server in PolicyLayer and add a rule for forget: 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 Brain MCP Server. Nothing to install.
forget 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 forget 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 forget. 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.
forget is provided by the Open Brain MCP Server MCP server (subwizzll/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 →