AI agents use update-stylesheet to create or update resources in Mcp Dev — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Dev environment.
This tool modifies stylesheets in an Umbraco CMS system, which is a reversible Write operation. The modification affects presentation layer files but is not destructive (can be reverted) and has bounded scope to a single stylesheet. Severity is medium due to potential impact on site appearance/functionality if modified incorrectly, but limited to CSS styling artifacts rather than core data or financial systems.
From the tool's definition Tool name explicitly states 'update-stylesheet' and description confirms it 'Updates a stylesheet by path', indicating modification of existing data.
Attacks that exploit this kind of access
Updates a stylesheet by path. It is categorised as a Write tool in the Mcp Dev MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Dev MCP server in PolicyLayer and add a rule for update-stylesheet: 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 Dev. Nothing to install.
update-stylesheet 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 update-stylesheet 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 update-stylesheet. 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.
update-stylesheet is provided by the Mcp Dev MCP server (@umbraco-cms/mcp-dev). 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 →