reply · Claude Intercom MCP: Risk & Policy

WHAT IT DOES

What reply does on Claude Intercom

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

WHY IT NEEDS A POLICY

Why reply needs a policy

The tool sends a message (creates new outbound data) and removes the original from the inbox. The removal aspect could be considered mildly destructive, but since it's an inbox management side-effect of a reply action (similar to 'mark as read/archive'), the dominant action is creating/sending a reply message — a Write operation.

From the tool's definition Reply to a specific message. Sends your response to the original sender and removes the original from your inbox.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

reply Rate-limited

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": {
    "reply": {
      "limits": [
        {
          "counter": "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 Claude Intercom, so you can run agents against it safely.

FAQ

Questions about reply

What does the reply tool do? +

Reply to a specific message. Sends your response to the original sender and removes the original from your inbox. Always reply to messages that ask you a question or request information. It is categorised as a Write tool in the Claude Intercom 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? +

Register the Claude Intercom MCP server in PolicyLayer and add a rule for 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 Claude Intercom. Nothing to install.

What risk level is reply? +

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

Can I rate-limit reply? +

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

Set action: deny in the PolicyLayer policy for 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 reply? +

reply is provided by the Claude Intercom MCP server (sanztheo/claude-intercom). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.