prepare_login

THE RISK

Medium Risk

Why prepare_login needs a policy

This tool creates or reinitializes login state artifacts (QR codes, tokens, or session data), which is a reversible modification of authentication data. It does not irreversibly delete data (not Destructive), does not execute arbitrary code (not Execute), and does not move money (not Financial).

From the tool's definition The tool name and description indicate it 'prepares' login artifacts and can 'force a fresh QR login flow,' which modifies authentication state and potentially overwrites existing login credentials or sessions.

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

POLICY

How to control prepare_login

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "prepare_login": {
      "limits": [
        {
          "counter": "prepare_login_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

prepare_login 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.

Create a free account and register 米家 MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More 米家 MCP Server tools

Destructive clear_saved_login Clear saved login credentials so the next connection triggers QR login. Execute execute_scene Execute a scene by friendly name or scene id. Execute control_by_intent Route a natural-language-like smart-home request to the best product tool. Execute control_device Control a device through capability operations like turn_on, set_brightness, set_target_te Execute reconnect_service Reconnect to Mijia cloud, optionally clearing saved login first. Execute turn_off_device Turn off a device. Execute turn_on_device Turn on a device. Execute set_cover_position Set position for any cover-capable device such as a curtain or blind.

All 26 米家 MCP Server tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about prepare_login

What does the prepare_login tool do? +

Prepare QR login artifacts and optionally force a fresh QR login flow. It is categorised as a Write tool in the 米家 MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on prepare_login? +

Register the 米家 MCP Server MCP server in PolicyLayer and add a rule for prepare_login: 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 米家 MCP Server. Nothing to install.

What risk level is prepare_login? +

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

Can I rate-limit prepare_login? +

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

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

prepare_login is provided by the 米家 MCP Server MCP server (javen-yan/miot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every 米家 MCP Server tool call.

Start from 米家 MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →