AI agents call clear_caches to permanently remove resources in MCP SQL Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cache clearing is a destructive operation that cannot be undone. While it may not directly affect primary data, clearing caches can cause cascading failures in database performance, query results consistency, and application functionality. In the context of a SQL server MCP with enterprise-grade operations, unauthorized cache clearing could severely impact system availability and data integrity verification.
From the tool's definition Tool name 'clear_caches' combined with description 'Initialize cache data' indicates irreversible deletion or overwriting of cached data. 'Clear' is a destructive operation that removes data without recovery mechanism.
Documented attack patterns abuse exactly the kind of access clear_caches gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP SQL Server, and nothing reaches the server without passing your rules. This is the rule we recommend for clear_caches:
{
"version": "1",
"default": "deny",
"hide": [
"clear_caches"
]
} clear_caches disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Initialize cache data. It is categorised as a Destructive tool in the MCP SQL Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP SQL Server MCP server in PolicyLayer and add a rule for clear_caches: 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 MCP SQL Server. Nothing to install.
clear_caches 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 clear_caches 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 clear_caches. 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.
clear_caches is provided by the MCP SQL Server MCP server (ryudg/mcp-sql). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP SQL Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
11 MCP SQL Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.