AI agents call cloud_remove_member to permanently remove resources in MCP ClickHouse — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a member from an organization is an irreversible action that revokes access and deletes the membership relationship. This cannot be easily undone without re-inviting the user, making it destructive in nature. The blast radius is high because it affects user access to potentially critical cloud infrastructure.
From the tool's definition Remove a member from the organization
Documented attack patterns abuse exactly the kind of access cloud_remove_member gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP ClickHouse, and nothing reaches the server without passing your rules. This is the rule we recommend for cloud_remove_member:
{
"version": "1",
"default": "deny",
"hide": [
"cloud_remove_member"
]
} cloud_remove_member 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.
Remove a member from the organization. It is categorised as a Destructive tool in the MCP ClickHouse MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP ClickHouse MCP server in PolicyLayer and add a rule for cloud_remove_member: 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 MCP ClickHouse. Nothing to install.
cloud_remove_member 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 cloud_remove_member 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 cloud_remove_member. 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.
cloud_remove_member is provided by the MCP ClickHouse MCP server (oualib/chmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP ClickHouse, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
55 MCP ClickHouse tools catalogued and risk-classified — across an index of 43,000+ MCP servers.