Delete a decision, finding, or mistake by ID.
AI agents call delete_entry to permanently remove resources in Project Brain — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes records from the project knowledge base without recovery mechanism. While the blast radius is limited to project documentation rather than production systems or financial assets, the action is irreversible and could cause significant harm if an AI agent deletes critical architectural decisions or lessons learned.
From the tool's definition Tool performs 'Delete a decision, finding, or mistake by ID' — an irreversible removal of data from the engineering memory system.
Attacks that exploit this kind of access
Delete a decision, finding, or mistake by ID. It is categorised as a Destructive tool in the Project Brain MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Project Brain MCP server in PolicyLayer and add a rule for delete_entry: 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 Project Brain. Nothing to install.
delete_entry 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 delete_entry 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 delete_entry. 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.
delete_entry is provided by the Project Brain MCP server (pym2282/project-brain-mcp). 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 →