Create a new SCIM resource. First use the
AI agents use createResource to create or update resources in SCIM MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SCIM MCP Server environment.
This tool creates new resources in a SCIM-compliant identity management system. While creation is reversible (the created resource can be deleted), it modifies system state and could create unwanted user accounts, groups, or other identity objects if misused by an AI agent.
From the tool's definition Tool name 'createResource' and function to 'Create a new SCIM resource' indicates it creates new data. SCIM 2.0 API operations for creating users, groups, and other identity resources are write operations that modify backend systems.
Attacks that exploit this kind of access
Create a new SCIM resource. First use the. It is categorised as a Write tool in the SCIM MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SCIM MCP Server MCP server in PolicyLayer and add a rule for createResource: 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 SCIM MCP Server. Nothing to install.
createResource 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 createResource 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 createResource. 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.
createResource is provided by the SCIM MCP Server MCP server (limosa-io/mcp-scim). 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 →