Completely replaces all existing privileges in a security role with a new set of privileges. WARNING: This removes all current privileges and replaces them with the specified ones. Use this for comprehensive role permission restructuring.
AI agents use replace_role_privileges to create or update resources in Dataverse MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dataverse MCP Server environment.
This tool modifies security role permissions in a system-wide manner. While privileges can technically be restored by reassigning them, the bulk replacement of all privileges in a role is a significant structural change to system access control. It does not irreversibly delete data (thus not Destructive) and does not execute code (thus not Execute), but it is a consequential Write operation.
From the tool's definition Tool description states it 'Completely replaces all existing privileges in a security role with a new set of privileges' and includes a WARNING about removing all current privileges.
Attacks that exploit this kind of access
Completely replaces all existing privileges in a security role with a new set of privileges. WARNING: This removes all current privileges and replaces them with the specified ones. Use this for comprehensive role permission restructuring. It is categorised as a Write tool in the Dataverse MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Dataverse MCP Server MCP server in PolicyLayer and add a rule for replace_role_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 Dataverse MCP Server. Nothing to install.
replace_role_privileges 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 replace_role_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 replace_role_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.
replace_role_privileges is provided by the Dataverse MCP Server MCP server (wizspdemo/dataverse-mcp2). 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 →