AI agents use sc_mark_for_add to create or update resources in Unreal — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Unreal environment.
This tool modifies source control staging state rather than directly creating/deleting files. It prepares files for commit but does not irreversibly change data. The operation is reversible (files can be unmarked or commits can be reverted). Classified as Write rather than Execute because it performs a specific administrative action on version control rather than arbitrary command execution.
From the tool's definition Tool name 'sc_mark_for_add' and description 'Mark new file(s) for add in source control' indicate the tool stages/marks files for addition to version control, which is a reversible data modification operation.
Attacks that exploit this kind of access
Mark new file(s) for add in source control. It is categorised as a Write tool in the Unreal MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Unreal MCP server in PolicyLayer and add a rule for sc_mark_for_add: 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 Unreal. Nothing to install.
sc_mark_for_add 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 sc_mark_for_add 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 sc_mark_for_add. 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.
sc_mark_for_add is provided by the Unreal MCP server (sam-david/unreal-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 →