Remove a saved connection configuration.
AI agents call kusto_connection_remove to permanently remove resources in Kusto MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a saved connection configuration is an irreversible deletion of stored data. Once removed, the connection configuration is gone and cannot be recovered without re-entering the details. This maps to the Destructive category. Severity is medium because it affects configuration/metadata rather than user data, but could disrupt workflows relying on that connection.
From the tool's definition 'Remove a saved connection configuration' — permanently deletes a stored connection entry
Attacks that exploit this kind of access
Remove a saved connection configuration. It is categorised as a Destructive tool in the Kusto MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Kusto MCP Server MCP server in PolicyLayer and add a rule for kusto_connection_remove: 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 Kusto MCP Server. Nothing to install.
kusto_connection_remove 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 kusto_connection_remove 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 kusto_connection_remove. 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.
kusto_connection_remove is provided by the Kusto MCP Server MCP server (yeshsurya/kusto-mcp-server). 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 →