删除整个知识库（危险操作！会删除所有数据）
AI agents call delete_database to permanently remove resources in RAG MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes an entire knowledge base and all associated data. It cannot be undone and represents total data loss for that database. This is the most severe category (Destructive) due to the permanent nature of the operation and the scale of data affected.
From the tool's definition Tool name 'delete_database' combined with description '删除整个知识库（危险操作！会删除所有数据）' which translates to 'Delete entire knowledge base (dangerous operation! will delete all data)'.
Attacks that exploit this kind of access
删除整个知识库（危险操作！会删除所有数据）. It is categorised as a Destructive tool in the RAG MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the RAG MCP Server MCP server in PolicyLayer and add a rule for delete_database: 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 RAG MCP Server. Nothing to install.
delete_database 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_database 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_database. 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_database is provided by the RAG MCP Server MCP server (sglwsjxh/rag-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 →