Use this when scan results seem stale or after making file changes that the server may not have detected. Clears the cached project index so the next nanostores_scan_project call performs a fresh scan.
AI agents call nanostores_clear_cache to permanently remove resources in Nanostores MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
rootUri | string | — | Workspace root to clear cache for. Omit to clear all roots. |
Parameters from the server's own tool schema.
The tool irreversibly clears/purges a cached index. While the data can be regenerated via a fresh scan and nothing permanent is lost, the act of clearing cache is a one-way destructive operation on the stored state. Severity is low because the cache is a derived artifact and can be rebuilt, so the blast radius of misuse is minimal.
From the tool's definition Clears the cached project index so the next nanostores_scan_project call performs a fresh scan
Attacks that exploit this kind of access
Use this when scan results seem stale or after making file changes that the server may not have detected. Clears the cached project index so the next nanostores_scan_project call performs a fresh scan. It is categorised as a Destructive tool in the Nanostores MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
nanostores_clear_cache accepts 1 parameter: rootUri. The full parameter table on this page comes from the server's own tool schema.
Register the Nanostores MCP server in PolicyLayer and add a rule for nanostores_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 Nanostores MCP. Nothing to install.
nanostores_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 nanostores_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 nanostores_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.
nanostores_clear_cache is provided by the Nanostores MCP server (nanostores-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 →