AI agents use create-user to create or update resources in Users — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Users environment.
This tool creates new user records, which is a reversible write operation. Severity is medium because creating unauthorized users could compromise system access control and user management integrity, but the operation is not destructive (can be undone by deletion) and carries no financial impact. The confidence is high given the explicit language in both the tool name and description.
From the tool's definition Tool name 'create-user' and description 'Create a new user in the database' explicitly indicate data creation. The server description confirms CRUD operations on users stored in a JSON file.
Attacks that exploit this kind of access
Create a new user in the database. It is categorised as a Write tool in the Users MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Users 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 Users. 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 Users MCP server (stormdotcom/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 →