AI agents use create-item to create or update resources in Itemit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Itemit environment.
This tool creates new data entries in the asset management system. It is reversible (items can be deleted or modified later), so it falls under Write rather than Destructive. The severity is medium because misuse could pollute the asset database with false records, but the impact is limited to asset metadata without financial or system-level consequences.
From the tool's definition Tool description states 'Create an item in Itemit' with parameters name, description, and serial. The create action modifies the asset database by adding new records.
Attacks that exploit this kind of access
Create an item in Itemit. Requires name, description, and serial. It is categorised as a Write tool in the Itemit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Itemit MCP server in PolicyLayer and add a rule for create-item: 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 Itemit. Nothing to install.
create-item 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-item 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-item. 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-item is provided by the Itemit MCP server (umin-ai/itemit-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 →