Create a new preset directory with manifest and token override scaffold, inheriting from a parent preset. Generates a ready-to-customize preset structure on disk. Args: - preset_id (string): Kebab-case ID for the new preset (e.g.
AI agents use scaffold_preset to create or update resources in UI Preset MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your UI Preset MCP Server environment.
This tool creates new data structures (preset directories, manifest files, token override scaffolds) on disk. It is a Write operation because it creates reversible artifacts that can be modified or deleted later. Severity is medium because misconfiguration or naming conflicts could create unintended preset structures, but the operation itself is non-destructive and doesn't affect existing presets or external systems.
From the tool's definition Tool description states it will "Create a new preset directory" and "Generates a ready-to-customize preset structure on disk." The arguments include a preset_id for naming. These actions create new files and directories on the filesystem.
Attacks that exploit this kind of access
Create a new preset directory with manifest and token override scaffold, inheriting from a parent preset. Generates a ready-to-customize preset structure on disk. Args: - preset_id (string): Kebab-case ID for the new preset (e.g. It is categorised as a Write tool in the UI Preset MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the UI Preset MCP Server MCP server in PolicyLayer and add a rule for scaffold_preset: 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 UI Preset MCP Server. Nothing to install.
scaffold_preset 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 scaffold_preset 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 scaffold_preset. 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.
scaffold_preset is provided by the UI Preset MCP Server MCP server (ncsound919/og-glass). 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 →