List the system privilege catalog. Use to discover privilegeId GUIDs and supported depths before assigning privileges to a role.
AI agents call list-privileges to retrieve information from PowerPlatform MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and enumerates system privilege information from the catalog. It performs no write, delete, execute, or financial operations. The purpose is informational—to help discover privilege identifiers before assignment. While the information could inform privilege escalation attacks if misused by an agent, the tool itself only reads data.
From the tool's definition Tool name is 'list-privileges' and description states 'List the system privilege catalog' and 'discover privilegeId GUIDs'. The verb 'list' and 'discover' indicate querying/retrieving metadata with no modifications or side effects.
Documented attack patterns abuse exactly the kind of access list-privileges gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PowerPlatform MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for list-privileges:
{
"version": "1",
"default": "deny",
"tools": {
"list-privileges": {}
}
} list-privileges is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List the system privilege catalog. Use to discover privilegeId GUIDs and supported depths before assigning privileges to a role. It is categorised as a Read tool in the PowerPlatform MCP MCP Server, which means it retrieves data without modifying state.
Register the PowerPlatform MCP server in PolicyLayer and add a rule for list-privileges: 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 PowerPlatform MCP. Nothing to install.
list-privileges is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list-privileges 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 list-privileges. 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.
list-privileges is provided by the PowerPlatform MCP server (michsob/powerplatform-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from PowerPlatform MCP, 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.
66 PowerPlatform MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.