set_root · Tome MCP: Risk & Policy

WHAT IT DOES

What set_root does on Tome

AI agents invoke set_root to trigger actions in Tome. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why set_root needs a policy

Changing the root directory at runtime redirects all subsequent file operations (PDF ingestion, bibliography management, figure tracking, etc.) to a new location. This is an Execute-level action because it triggers a runtime configuration change whose effects propagate to all downstream operations, potentially causing the server to read from or write to unintended directories.

From the tool's definition Switch Tome's project root directory at runtime

Risk signalsAdmin/system-level operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

set_root Rate-limited

set_root stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "set_root": {
      "limits": [
        {
          "counter": "set_root_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about set_root

What does the set_root tool do? +

Switch Tome's project root directory at runtime. It is categorised as a Execute tool in the Tome MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on set_root? +

Register the Tome MCP server in PolicyLayer and add a rule for set_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 Tome. Nothing to install.

What risk level is set_root? +

set_root is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit set_root? +

Yes. Add a rate_limit block to the set_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 set_root completely? +

Set action: deny in the PolicyLayer policy for set_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 set_root? +

set_root is provided by the Tome MCP server (retospect/tome-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.