Update an existing role
AI agents use update_role to create or update resources in Looker MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Looker MCP Server environment.
This tool performs reversible modification of role objects in Looker. While role changes can affect access control and permissions across the system (potentially impacting many users), the change itself is not destructive—a previously granted role can be modified back or replaced. This places it in the Write category rather than Execute or Destructive.
From the tool's definition Tool is described as 'Update an existing role', which modifies an existing role definition reversibly. Role updates are configuration changes that can be undone or corrected by subsequent updates.
Attacks that exploit this kind of access
Update an existing role. It is categorised as a Write tool in the Looker MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Looker MCP Server MCP server in PolicyLayer and add a rule for update_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 Looker MCP Server. Nothing to install.
update_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 update_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 update_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.
update_role is provided by the Looker MCP Server MCP server (ultrathink-solutions/looker-mcp-server). 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 →