export_to_unity
AI agents use export_to_unity to create or update resources in ComfyMCP Studio — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ComfyMCP Studio environment.
Export operations write data to target systems (Unity projects). While not destructive (the export doesn't delete source assets) or execute (not running arbitrary code), this is a Write action that creates or modifies files/project data in Unity. Severity is medium because misuse could corrupt a game project or write unwanted assets, but it's reversible and scoped to asset export rather than critical system access.
From the tool's definition Tool named 'export_to_unity' on a server that generates 2D game assets and explicitly supports 'Unity export'.
Attacks that exploit this kind of access
export_to_unity. It is categorised as a Write tool in the ComfyMCP Studio MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ComfyMCP Studio MCP server in PolicyLayer and add a rule for export_to_unity: 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 ComfyMCP Studio. Nothing to install.
export_to_unity 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 export_to_unity 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 export_to_unity. 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.
export_to_unity is provided by the ComfyMCP Studio MCP server (tuannguyen14/comfyai-mcp-gameassets). 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 →