AI agents use create_item to create or update resources in miniMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your miniMCP environment.
The tool creates new data in an in-memory database, which is reversible (items can be deleted via the sibling delete_item tool). This is classic Write category behavior. Severity is medium because unauthorized or malicious item creation could pollute the database and consume resources, but the in-memory nature and reversibility prevent it from being high/critical.
From the tool's definition Tool name 'create_item' and description 'Create a new item in the database' directly indicate data creation/insertion, which is a Write operation.
Attacks that exploit this kind of access
Create a new item in the database. It is categorised as a Write tool in the miniMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the mini 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 miniMCP. 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 mini MCP server (lihn2254/minimcp). 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 →