risk_policy_set · LocalAnt MCP: Risk & Policy

WHAT IT DOES

What risk_policy_set does on LocalAnt

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

WHY IT NEEDS A POLICY

Why risk_policy_set needs a policy

This tool modifies the security/approval policy governing which actions require human approval. Misuse could disable safety guardrails (e.g., setting risk-1 actions to not need approval), allowing an AI agent to subsequently execute destructive or dangerous operations without oversight.

From the tool's definition 'Set the risk policy (mode and/or whether risk-1 actions need approval)'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

risk_policy_set Rate-limited

risk_policy_set 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": {
    "risk_policy_set": {
      "limits": [
        {
          "counter": "risk_policy_set_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 LocalAnt, so you can run agents against it safely.

FAQ

Questions about risk_policy_set

What does the risk_policy_set tool do? +

Set the risk policy (mode and/or whether risk-1 actions need approval). It is categorised as a Write tool in the LocalAnt MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on risk_policy_set? +

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

What risk level is risk_policy_set? +

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

Can I rate-limit risk_policy_set? +

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

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

risk_policy_set is provided by the LocalAnt MCP server (yuga-hashimoto/localant). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.