AI agents use romm_remove_from_collection to create or update resources in Mcp Romm — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Romm environment.
The tool removes ROMs from a collection but explicitly does not delete the collection itself. This is a reversible modification (ROMs can be re-added), making it a Write operation rather than Destructive. Misuse could disrupt a user's organized collections but the data is not permanently destroyed.
From the tool's definition Remove one or more ROMs from a collection (without deleting the collection)
Attacks that exploit this kind of access
Remove one or more ROMs from a collection (without deleting the collection). It is categorised as a Write tool in the Mcp Romm MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Romm MCP server in PolicyLayer and add a rule for romm_remove_from_collection: 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 Mcp Romm. Nothing to install.
romm_remove_from_collection 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 romm_remove_from_collection 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 romm_remove_from_collection. 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.
romm_remove_from_collection is provided by the Mcp Romm MCP server (lodordev/mcp-romm). 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 →