save_roles_plan · Backend Architect MCP Server MCP

WHAT IT DOES

What save_roles_plan does on Backend Architect MCP Server

AI agents use save_roles_plan to create or update resources in Backend Architect MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Backend Architect MCP Server environment.

WHY IT NEEDS A POLICY

Why save_roles_plan needs a policy

This tool creates or modifies role-based access control (RBAC) definitions in project state. While not destructive (changes are reversible via state updates), it is a Write operation that modifies sensitive security configuration. Severity is high because misconfiguration of roles and permissions can grant unintended access to backend resources, create privilege escalation vectors, or expose sensitive functionality.

From the tool's definition Tool name 'save_roles_plan' indicates writing/persisting data. Description states it 'Saves user roles/permissions to state', which is a create/modify operation that persists configuration data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_roles_plan Rate-limited

save_roles_plan 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "save_roles_plan": {
      "limits": [
        {
          "counter": "save_roles_plan_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Backend Architect MCP Server, so you can run agents against it safely.

FAQ

Questions about save_roles_plan

What does the save_roles_plan tool do? +

Saves user roles/permissions to state. Each role should have 'name', 'description', and 'permissions'. It is categorised as a Write tool in the Backend Architect MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on save_roles_plan? +

Register the Backend Architect MCP Server MCP server in PolicyLayer and add a rule for save_roles_plan: 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 Backend Architect MCP Server. Nothing to install.

What risk level is save_roles_plan? +

save_roles_plan is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit save_roles_plan? +

Yes. Add a rate_limit block to the save_roles_plan 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.

How do I block save_roles_plan completely? +

Set action: deny in the PolicyLayer policy for save_roles_plan. 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.

What MCP server provides save_roles_plan? +

save_roles_plan is provided by the Backend Architect MCP Server MCP server (jemhakdog/mcp_fastapi). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.