Clears the embeddings cache, forcing a complete reindex on next search or manual index operation. Useful when encountering cache corruption or after major codebase changes.
AI agents call c_clear_cache to permanently remove resources in Smart Coding MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing the embeddings cache irreversibly destroys all precomputed embeddings data, requiring a full reindex. This is a destructive, non-reversible deletion of cached data. While the cache can be rebuilt (reducing severity), the action itself is irreversible and could cause significant disruption (loss of search functionality until reindex completes, which may be time-consuming for large codebases).
From the tool's definition 'Clears the embeddings cache, forcing a complete reindex on next search or manual index operation'
Documented attack patterns abuse exactly the kind of access c_clear_cache gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Smart Coding MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for c_clear_cache:
{
"version": "1",
"default": "deny",
"hide": [
"c_clear_cache"
]
}c_clear_cache 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.
Clears the embeddings cache, forcing a complete reindex on next search or manual index operation. Useful when encountering cache corruption or after major codebase changes. It is categorised as a Destructive tool in the Smart Coding MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Smart Coding MCP server in PolicyLayer and add a rule for c_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 Smart Coding MCP. Nothing to install.
c_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 c_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 c_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.
c_clear_cache is provided by the Smart Coding MCP server (omar-haris/smart-coding-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Smart Coding MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
6 Smart Coding MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.