Remove a role grant from a user by grant ID. Requires confirm: true.
AI agents call zitadel_remove_user_grant to permanently remove resources in Zitadel MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes or revokes access control permissions (role grants). While not a direct data deletion, removing user grants fundamentally alters authorization state in a way that cannot be automatically restored. This fits the Destructive category more precisely than Write, as the operation severs permissions rather than modifying them reversibly.
From the tool's definition The tool name explicitly uses 'remove' and the description states it 'Remove[s] a role grant from a user by grant ID.' Removing a role grant is an irreversible operation that revokes access permissions and cannot be undone without re-granting the role.
Documented attack patterns abuse exactly the kind of access zitadel_remove_user_grant gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Zitadel MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for zitadel_remove_user_grant:
{
"version": "1",
"default": "deny",
"hide": [
"zitadel_remove_user_grant"
]
} zitadel_remove_user_grant 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 role grant from a user by grant ID. Requires confirm: true. It is categorised as a Destructive tool in the Zitadel MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Zitadel MCP server in PolicyLayer and add a rule for zitadel_remove_user_grant: 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 Zitadel MCP. Nothing to install.
zitadel_remove_user_grant 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 zitadel_remove_user_grant 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 zitadel_remove_user_grant. 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.
zitadel_remove_user_grant is provided by the Zitadel MCP server (takleb3rry/zitadel-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Zitadel MCP, 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.
26 Zitadel MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.