AI agents use security-new-role to create or update resources in Mcp Sitecore — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Sitecore environment.
This tool creates a new security role in Sitecore, which is a reversible write operation. However, it carries high severity because creating roles can affect access control and security posture across the Sitecore instance — a misused or maliciously named role could be used to grant unintended permissions.
From the tool's definition Creates a new Sitecore role
Documented attack patterns abuse exactly the kind of access security-new-role gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Sitecore, and nothing reaches the server without passing your rules. This is the rule we recommend for security-new-role:
{
"version": "1",
"default": "deny",
"tools": {
"security-new-role": {
"limits": [
{
"counter": "security-new-role_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}security-new-role stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Creates a new Sitecore role. It is categorised as a Write tool in the Mcp Sitecore MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Sitecore MCP server in PolicyLayer and add a rule for security-new-role: 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 Sitecore. Nothing to install.
security-new-role 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 security-new-role 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 security-new-role. 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.
security-new-role is provided by the Mcp Sitecore MCP server (@antonytm/mcp-sitecore-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Sitecore, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
149 Mcp Sitecore tools catalogued and risk-classified — across an index of 43,000+ MCP servers.