Medium Risk

init_root

Initialize or set the project root directory for the current session.

How to control init_root ↓

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

Medium Risk

This tool writes/sets configuration state (the project root) but does not delete data, execute arbitrary code, or trigger financial operations. The impact is reversible within a session, making it Write rather than Execute or Destructive. Severity is medium because misconfiguration could affect downstream tool behavior and data access scope, but the effect is limited to the current session context.

From the tool's definition Tool description states it will "Initialize or set the project root directory" — a state-changing operation that modifies session configuration.

Risk signalsAdmin/system-level operation

Documented attack patterns abuse exactly the kind of access init_root gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and Scopecraft Command, and nothing reaches the server without passing your rules. This is the rule we recommend for init_root:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "init_root": {
      "limits": [
        {
          "counter": "init_root_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

init_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.

  1. Create a free account and register Scopecraft Command — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the init_root tool do? +

Initialize or set the project root directory for the current session. It is categorised as a Write tool in the Scopecraft Command MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on init_root? +

Register the Scopecraft Command MCP server in PolicyLayer and add a rule for init_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 Scopecraft Command. Nothing to install.

What risk level is init_root? +

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

Can I rate-limit init_root? +

Yes. Add a rate_limit block to the init_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 init_root completely? +

Set action: deny in the PolicyLayer policy for init_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 init_root? +

init_root is provided by the Scopecraft Command MCP server (scopecraft/command). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Scopecraft Command tool call.

Deterministic rules across all 18 Scopecraft Command tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

18 Scopecraft Command tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.