bottle_reply · Cartridge MCP: Risk & Policy

WHAT IT DOES

What bottle_reply does on Cartridge

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

WHY IT NEEDS A POLICY

Why bottle_reply needs a policy

The tool sends a reply to an existing 'bottle' (message/conversation entity), which is a write operation that creates new data (a reply message). It modifies state reversibly by adding a response to an existing item. Severity is medium as misuse could send unintended messages in conversations.

From the tool's definition Reply to a specific bottle

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

bottle_reply Rate-limited

bottle_reply 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": {
    "bottle_reply": {
      "limits": [
        {
          "counter": "bottle_reply_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 Cartridge, so you can run agents against it safely.

FAQ

Questions about bottle_reply

What does the bottle_reply tool do? +

Reply to a specific bottle. It is categorised as a Write tool in the Cartridge MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on bottle_reply? +

Register the Cartridge MCP server in PolicyLayer and add a rule for bottle_reply: 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 Cartridge. Nothing to install.

What risk level is bottle_reply? +

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

Can I rate-limit bottle_reply? +

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

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

bottle_reply is provided by the Cartridge MCP server (lucineer/cartridge-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.