set_confirm_mode · AF_ MCP: Risk & Policy

Q: What does the set_confirm_mode tool do?

设置当前进程内全局确认模式，可切换为 手动 或 自动。. It is categorised as a Execute tool in the AF_MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

WHAT IT DOES

What set_confirm_mode does on AF_MCP

AI agents invoke set_confirm_mode to trigger actions in AF_MCP. 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_confirm_mode needs a policy

This tool modifies the global confirmation mode controlling how security operations (device blocking/unblocking) are approved. Switching from manual to automatic confirmation could allow all subsequent destructive or security-critical operations (blacklisting, unblocking) to execute without human review, significantly amplifying the blast radius of any misuse.

From the tool's definition 设置当前进程内全局确认模式，可切换为手动或自动 (sets global confirmation mode for the current process, switchable between manual and automatic)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

set_confirm_mode Rate-limited

set_confirm_mode 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_confirm_mode": {
      "limits": [
        {
          "counter": "set_confirm_mode_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 AF_MCP, so you can run agents against it safely.

FAQ

Questions about set_confirm_mode

What does the set_confirm_mode tool do? +

设置当前进程内全局确认模式，可切换为手动或自动。. It is categorised as a Execute tool in the AF_MCP 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_confirm_mode? +

Register the AF_ MCP server in PolicyLayer and add a rule for set_confirm_mode: 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 AF_MCP. Nothing to install.

What risk level is set_confirm_mode? +

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

Can I rate-limit set_confirm_mode? +

Yes. Add a rate_limit block to the set_confirm_mode 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_confirm_mode completely? +

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

set_confirm_mode is provided by the AF_ MCP server (xiaqijun/af_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.