semantic_clear

Delete all indexed data from the local vector store AND remove corresponding entries from macOS Spotlight.

SERVERIconnect SOURCEiconnect-mcp

Critical RISK CLASS

Category Destructive

Parameters 00 required

Recommended Hiddensee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-heznpc-iconnect/semantic-clear.md

WHAT IT DOES

What semantic_clear does on Iconnect

AI agents call semantic_clear to permanently remove resources in Iconnect, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

RISK

Why semantic_clear is rated Critical

The tool irreversibly deletes all indexed data from a vector store and removes entries from macOS Spotlight. These are destructive operations that cannot be undone—data loss is permanent. The 'Delete all' scope amplifies the risk. While not affecting financial systems or external services, the destruction of a complete local index represents significant data loss that warrants 'high' severity.

From the tool's definition Delete all indexed data from the local vector store AND remove corresponding entries from macOS Spotlight.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs semantic_clear safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Iconnect, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For semantic_clear, this is the rule to start with:

semantic_clear Hidden

semantic_clear is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "semantic_clear"
  ]
}

RESTRICT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Iconnect, apply this rule, and every semantic_clear call is checked against it from then on.

FAQ

Questions about semantic_clear

What does the semantic_clear tool do? +

Delete all indexed data from the local vector store AND remove corresponding entries from macOS Spotlight. It is categorised as a Destructive tool in the Iconnect MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on semantic_clear? +

Register the Iconnect MCP server in PolicyLayer and add a rule for semantic_clear: 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 Iconnect. Nothing to install.

What risk level is semantic_clear? +

semantic_clear is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit semantic_clear? +

Yes. Add a rate_limit block to the semantic_clear 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.

How do I block semantic_clear completely? +

Set action: deny in the PolicyLayer policy for semantic_clear. 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.

What MCP server provides semantic_clear? +

semantic_clear is provided by the Iconnect MCP server (iconnect-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Iconnect, and thousands of servers like it.

This server

All 279 Iconnect tools → Critical-risk tools on this server →

Across the catalogue

clear_renders on Why Did You Render →knowledge_clear on Templonix Lite MCP Server →clear_scan on Frida Game Hacking MCP →clear_spam_box on cPanel MCP Server → All critical-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Blast radius →Tool call approval →