🔄 Clear cached chunks and position index. Call this after modifying the document to ensure fresh data on next read operation.
Part of the Hwpx MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents may call invalidate_reading_cache to permanently remove or destroy resources in Hwpx. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. Intercept blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call invalidate_reading_cache in a loop, permanently destroying resources in Hwpx. There is no undo for destructive operations. Intercept blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
tools:
invalidate_reading_cache:
rules:
- action: deny
reason: "Blocked by default — enable with approval"See the full Hwpx policy for all 135 tools.
Agents calling destructive-class tools like invalidate_reading_cache have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Destructive risk category across the catalogue. The same policy patterns (deny, require_approval) apply to each.
invalidate_reading_cache is one of the critical-risk operations in Hwpx. For the full severity-focused view — only the critical-risk tools with their recommended policies — see the breakdown for this server, or browse all critical-risk tools across every MCP server.
🔄 Clear cached chunks and position index. Call this after modifying the document to ensure fresh data on next read operation.. It is categorised as a Destructive tool in the Hwpx MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Add a rule in your Intercept YAML policy under the tools section for invalidate_reading_cache. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Hwpx MCP server.
invalidate_reading_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 invalidate_reading_cache rule in your Intercept 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 Intercept policy for invalidate_reading_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.
invalidate_reading_cache is provided by the Hwpx MCP server (hwpx-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.