AI agents use create-user to create or update resources in Keycloak — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Keycloak environment.
This tool creates a new user account, which is a reversible write operation. While it modifies system state by adding an identity to the authentication system, the action can be undone by deleting the user (as evidenced by the sibling 'delete-user' tool). It does not execute arbitrary code, delete data irreversibly, or move money, so it falls under Write rather than Execute, Destructive, or Financial.
From the tool's definition Tool name 'create-user' combined with description 'Create a new user in a specific realm' indicates creation of new data in Keycloak.
Attacks that exploit this kind of access
Create a new user in a specific realm. It is categorised as a Write tool in the Keycloak MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Keycloak MCP server in PolicyLayer and add a rule for create-user: 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 Keycloak. Nothing to install.
create-user is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create-user 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 create-user. 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.
create-user is provided by the Keycloak MCP server (keycloak-mcp). 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 →