Delete project hive and all associated knowledge entries. Use this to start fresh or remove a project
AI agents call delete_hive to permanently remove resources in Hivemind MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes data without recovery options (no undo mentioned). The blast radius is high because an AI agent misusing this could wipe out accumulated project knowledge, debugging solutions, and learned skills that the team depends on. While not financial or system-level destructive, it causes significant data loss within the knowledge management system.
From the tool's definition 'Delete project hive and all associated knowledge entries' - the tool irreversibly removes an entire knowledge base and all stored solutions/debugging information for a project.
Attacks that exploit this kind of access
Delete project hive and all associated knowledge entries. Use this to start fresh or remove a project. It is categorised as a Destructive tool in the Hivemind MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Hivemind MCP server in PolicyLayer and add a rule for delete_hive: 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 Hivemind MCP. Nothing to install.
delete_hive 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_hive 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_hive. 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_hive is provided by the Hivemind MCP server (kevthetech143/hivemind-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 →