Delete a knowledge entry by title from a topic. Use to remove stale or moved entries.
AI agents call deleteKnowledge to permanently remove resources in Knowledge 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 (knowledge entries) from the GitHub-backed knowledge base. Deletion operations are irreversible and cannot be undone without manual recovery from git history.
From the tool's definition Tool name is 'deleteKnowledge' and description explicitly states 'Delete a knowledge entry by title from a topic.
Attacks that exploit this kind of access
Delete a knowledge entry by title from a topic. Use to remove stale or moved entries. It is categorised as a Destructive tool in the Knowledge MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Knowledge MCP Server MCP server in PolicyLayer and add a rule for deleteKnowledge: 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 Knowledge MCP Server. Nothing to install.
deleteKnowledge 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 deleteKnowledge 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 deleteKnowledge. 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.
deleteKnowledge is provided by the Knowledge MCP Server MCP server (vuluu2k/knowledge_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 →