reply_to_companion · Yocoolab MCP: Risk & Policy

WHAT IT DOES

What reply_to_companion does on Yocoolab

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

WHY IT NEEDS A POLICY

Why reply_to_companion needs a policy

This tool creates/modifies data (chat messages in the companion UI) in a reversible manner. It sends text replies to a chat interface, which is a write operation. The blast radius is minimal—the worst outcome is spam or misleading messages in the companion chat, which can be deleted or dismissed. No financial, destructive, or code execution implications.

From the tool's definition Send a reply back to the AI Companion panel in the Chrome extension. The reply will appear as an assistant message in the companion chat UI.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

reply_to_companion Rate-limited

reply_to_companion 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": {
    "reply_to_companion": {
      "limits": [
        {
          "counter": "reply_to_companion_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 Yocoolab, so you can run agents against it safely.

FAQ

Questions about reply_to_companion

What does the reply_to_companion tool do? +

Send a reply back to the AI Companion panel in the Chrome extension. The reply will appear as an assistant message in the companion chat UI. Supports Markdown formatting. It is categorised as a Write tool in the Yocoolab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on reply_to_companion? +

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

What risk level is reply_to_companion? +

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

Can I rate-limit reply_to_companion? +

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

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

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