AI agents use sc_checkin 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.
Checking in files to source control creates new commits/versions and modifies the repository state. While reversible (prior versions remain accessible and commits can be reverted), this is a write operation that introduces changes to the tracked codebase. The severity is medium because misuse could pollute the repository history or introduce unwanted code, but commits can be reverted and are auditable.
From the tool's definition Tool name 'sc_checkin' and description 'Check in file(s) to source control with a description' indicates it modifies source control state by committing/checking in files, which is a reversible write operation to a version control system.
Attacks that exploit this kind of access
Check in file(s) to source control with a description. 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_checkin: 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_checkin 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_checkin 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_checkin. 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_checkin 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 →