manage_livestream · Pancake POS MCP: Risk & Policy

WHAT IT DOES

What manage_livestream does on Pancake POS MCP

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

WHY IT NEEDS A POLICY

Why manage_livestream needs a policy

This tool spans multiple categories: Read (list, get), Write (create, update), and Destructive (delete). However, deleting a livestream session is typically reversible or low-impact compared to deleting customer, financial, or inventory data—it removes a session record but not irreplaceable transactional data. The most severe and likely primary use case is Write (creating/updating livestream configurations).

From the tool's definition Tool description states actions include 'list, get, create, update, delete' for livestream sessions. While delete is present, the primary purpose is managing (create, update) livestream data rather than permanently destroying core business records.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

manage_livestream Rate-limited

manage_livestream 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": {
    "manage_livestream": {
      "limits": [
        {
          "counter": "manage_livestream_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 Pancake POS MCP, so you can run agents against it safely.

FAQ

Questions about manage_livestream

What does the manage_livestream tool do? +

Manage live selling sessions (livestreams) in Pancake POS. Actions: list, get, create, update, delete. It is categorised as a Write tool in the Pancake POS MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on manage_livestream? +

Register the Pancake POS MCP server in PolicyLayer and add a rule for manage_livestream: 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 Pancake POS MCP. Nothing to install.

What risk level is manage_livestream? +

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

Can I rate-limit manage_livestream? +

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

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

manage_livestream is provided by the Pancake POS MCP server (svn4pro/pancake-pos-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.