删除键（需要关闭只读模式）
AI agents call delete_keys to permanently remove resources in Redis — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The delete_keys tool irreversibly removes data from the Redis database. This is a destructive operation that cannot be undone and could cause significant data loss if misused by an AI agent. Even with the read-only mode protection mentioned in the server description, this tool explicitly requires that protection to be disabled, making it the most severe category applicable.
From the tool's definition Tool name is 'delete_keys' and description states '删除键' (delete keys), which directly indicates irreversible data deletion. The note '(需要关闭只读模式)' confirms this requires disabling read-only mode, a safety constraint for destructive operations.
Attacks that exploit this kind of access
删除键（需要关闭只读模式）. It is categorised as a Destructive tool in the Redis MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Redis MCP server in PolicyLayer and add a rule for delete_keys: 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 Redis. Nothing to install.
delete_keys 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_keys 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_keys. 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_keys is provided by the Redis MCP server (lm203688/redis-mcp-server). 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 →