AI agents use create_user to create or update resources in Mcp Sling — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Sling environment.
The tool creates a new user account, which modifies organizational data in a reversible way (users can be deactivated or deleted). This is a Write category operation. Severity is high because unauthorized user creation could grant unauthorized access to the workforce management system, disrupt scheduling, and affect payroll or operational decisions.
From the tool's definition Tool name: 'create_user'; description states 'Create a new user in the organization' — this is a write operation that creates a new entity in the system.
Attacks that exploit this kind of access
Create a new user in the organization. It is categorised as a Write tool in the Mcp Sling MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Sling 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 Mcp Sling. 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 Mcp Sling MCP server (poncheck/mcp-sling). 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 →