High Risk →

real_device_preview

Build and upload the game to WeChat for real device preview. Returns a QR code that the user can scan with WeChat. Requires AppID and upload private key (configurable via env vars or browser UI).

Part of the Weixin Minigame Helper server.

real_device_preview can trigger actions in Weixin Minigame Helper, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE WEIXIN MINIGAME HELPER →

Free to start. No card required.

AI agents invoke real_device_preview to trigger processes or run actions in Weixin Minigame Helper. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.

real_device_preview can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.

Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "real_device_preview": {
      "limits": [
        {
          "counter": "real_device_preview_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Weixin Minigame Helper policy for all 6 tools.

Get this rule live on your own Weixin Minigame Helper server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY WEIXIN MINIGAME HELPER →

These attack patterns abuse exactly the kind of access real_device_preview gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so real_device_preview only ever does what you allow.

SECURE WEIXIN MINIGAME HELPER →

Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the real_device_preview tool do? +

Build and upload the game to WeChat for real device preview. Returns a QR code that the user can scan with WeChat. Requires AppID and upload private key (configurable via env vars or browser UI).. It is categorised as a Execute tool in the Weixin Minigame Helper MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on real_device_preview? +

Register the Weixin Minigame Helper MCP server in PolicyLayer and add a rule for real_device_preview: 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 Weixin Minigame Helper. Nothing to install.

What risk level is real_device_preview? +

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

Can I rate-limit real_device_preview? +

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

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

real_device_preview is provided by the Weixin Minigame Helper MCP server (@weadmin/weixin-minigame-helper-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Weixin Minigame Helper tool call.

Deterministic rules across all 6 Weixin Minigame Helper tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.