[DANGER] 删除知识 - 物理删除指定的知识条目。
AI agents call delete_knowledge to permanently remove resources in Adaptive Agent — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes knowledge entries from the system's memory and knowledge graph. Unlike reversible write operations (create, update), deletion cannot be undone. In the context of a self-evolving RAG system that maintains user preferences, daily logs, and knowledge graphs, unauthorized or mistaken deletion could cause permanent loss of critical contextual data that the AI agent relies upon.
From the tool's definition Tool name is 'delete_knowledge' and description explicitly states '物理删除指定的知识条目' (physically delete specified knowledge entries). The [DANGER] prefix in the description further signals destructive intent.
Attacks that exploit this kind of access
[DANGER] 删除知识 - 物理删除指定的知识条目。. It is categorised as a Destructive tool in the Adaptive Agent MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Adaptive Agent MCP server in PolicyLayer and add a rule for delete_knowledge: 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 Adaptive Agent. Nothing to install.
delete_knowledge 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_knowledge 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_knowledge. 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_knowledge is provided by the Adaptive Agent MCP server (justforever17/adaptive-agent-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 →