add_allowed_root · Unlimited MCP: Risk & Policy

WHAT IT DOES

What add_allowed_root does on Unlimited

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

WHY IT NEEDS A POLICY

Why add_allowed_root needs a policy

This tool creates or modifies configuration entries (Write category). It is not Destructive because the modification is reversible—roots can presumably be removed. It is not Read because it mutates state. The severity is high because misconfiguration of filesystem access boundaries could grant unintended access to sensitive directories, expanding the attack surface for the background agents.

From the tool's definition The tool description states it 'Add[s] a filesystem path to allowed_roots', which modifies configuration data that controls filesystem access boundaries. The verb 'add' indicates write/create semantics.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_allowed_root Rate-limited

add_allowed_root 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": {
    "add_allowed_root": {
      "limits": [
        {
          "counter": "add_allowed_root_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 Unlimited, so you can run agents against it safely.

FAQ

Questions about add_allowed_root

What does the add_allowed_root tool do? +

Add a filesystem path to allowed_roots. It is categorised as a Write tool in the Unlimited MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_allowed_root? +

Register the Unlimited MCP server in PolicyLayer and add a rule for add_allowed_root: 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 Unlimited. Nothing to install.

What risk level is add_allowed_root? +

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

Can I rate-limit add_allowed_root? +

Yes. Add a rate_limit block to the add_allowed_root 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 add_allowed_root completely? +

Set action: deny in the PolicyLayer policy for add_allowed_root. 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 add_allowed_root? +

add_allowed_root is provided by the Unlimited MCP server (triumsebas/unlimited-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.