Create a new database user
AI agents use user_create to create or update resources in MongoDB Atlas MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MongoDB Atlas MCP Server environment.
Creating database users is a reversible write operation that modifies system state by adding new authentication principals. However, it carries high severity because it can grant unauthorized access to sensitive data if misused by an AI agent. The blast radius extends to potential data breaches if the agent creates overprivileged users or users for malicious purposes.
From the tool's definition Tool name 'user_create' and description 'Create a new database user' indicate creation of a new user account with database access permissions.
Attacks that exploit this kind of access
Create a new database user. It is categorised as a Write tool in the MongoDB Atlas MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MongoDB Atlas MCP Server MCP server in PolicyLayer and add a rule for user_create: 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 MongoDB Atlas MCP Server. Nothing to install.
user_create 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 user_create 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 user_create. 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.
user_create is provided by the MongoDB Atlas MCP Server MCP server (montumodi/mongodb-atlas-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 →