Get the 4-step workflow for adding a new permission: enum → seeder → superadmin assigns → @RequiresPermission().
AI agents call rbac_get_permission_pattern to retrieve information from LaunchFrame MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about RBAC permission patterns and workflows. It has no side effects, does not execute code, does not modify data, and does not trigger external operations. It is purely informational, serving to help agents understand existing architectural patterns.
From the tool's definition Tool name includes 'get' and description states 'Get the 4-step workflow' — retrieves architectural documentation and implementation patterns without modifying data or triggering deployments.
Attacks that exploit this kind of access
Get the 4-step workflow for adding a new permission: enum → seeder → superadmin assigns → @RequiresPermission(). It is categorised as a Read tool in the LaunchFrame MCP MCP Server, which means it retrieves data without modifying state.
Register the LaunchFrame MCP server in PolicyLayer and add a rule for rbac_get_permission_pattern: 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 LaunchFrame MCP. Nothing to install.
rbac_get_permission_pattern 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 rbac_get_permission_pattern 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 rbac_get_permission_pattern. 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.
rbac_get_permission_pattern is provided by the LaunchFrame MCP server (launchframe-dev/mcp). 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 →