approval_approve · LocalAnt MCP: Risk & Policy

WHAT IT DOES

What approval_approve does on LocalAnt

AI agents invoke approval_approve to trigger actions in LocalAnt. 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 approval_approve needs a policy

Approving a pending request is an Execute-class action because it authorizes and triggers the execution of another operation. Given the server context (shell commands, file management, browser automation, ADB device control), the pending requests could involve high-impact operations.

From the tool's definition 'Approve a pending request' — this triggers authorization of a previously queued action, causing downstream execution of whatever was pending approval.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

approval_approve Rate-limited

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

FAQ

Questions about approval_approve

What does the approval_approve tool do? +

Approve a pending request. scope. It is categorised as a Execute tool in the LocalAnt MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on approval_approve? +

Register the LocalAnt MCP server in PolicyLayer and add a rule for approval_approve: 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 approval_approve? +

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

Can I rate-limit approval_approve? +

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

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

approval_approve 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.