Clear cached indices
AI agents call clear_cache to permanently remove resources in Code Search MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing cached indices irreversibly removes stored index data that was built up over time. While the cache can theoretically be rebuilt via refresh_index, the act of clearing is a one-way destructive operation on the cached data. Misuse could cause significant performance degradation and loss of indexed state, warranting a medium severity rating since the underlying source data is not affected.
From the tool's definition 'Clear cached indices' — clears/purges the persistent cache used for optimized performance
Attacks that exploit this kind of access
Clear cached indices. It is categorised as a Destructive tool in the Code Search MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Code Search MCP server in PolicyLayer and add a rule for clear_cache: 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 Code Search MCP. Nothing to install.
clear_cache 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_cache 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_cache. 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_cache is provided by the Code Search MCP server (llmtooling/code-search-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 →