keyid_reply · KeyID Agent Kit MCP: Risk & Policy

WHAT IT DOES

What keyid_reply does on KeyID Agent Kit

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

WHY IT NEEDS A POLICY

Why keyid_reply needs a policy

This tool sends an email reply, which creates new outbound email data. It is a write operation (composing and sending a message) with moderate blast radius — an AI agent could send unwanted replies to arbitrary threads, potentially leaking information or causing reputational harm, but it is reversible in the sense that the action is bounded to a single message send.

From the tool's definition Reply to a message. Automatically sets subject, thread, and in-reply-to headers.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

keyid_reply Rate-limited

keyid_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": {
    "keyid_reply": {
      "limits": [
        {
          "counter": "keyid_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 KeyID Agent Kit, so you can run agents against it safely.

FAQ

Questions about keyid_reply

What does the keyid_reply tool do? +

Reply to a message. Automatically sets subject, thread, and in-reply-to headers. It is categorised as a Write tool in the KeyID Agent Kit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on keyid_reply? +

Register the KeyID Agent Kit MCP server in PolicyLayer and add a rule for keyid_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 KeyID Agent Kit. Nothing to install.

What risk level is keyid_reply? +

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

Can I rate-limit keyid_reply? +

Yes. Add a rate_limit block to the keyid_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 keyid_reply completely? +

Set action: deny in the PolicyLayer policy for keyid_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 keyid_reply? +

keyid_reply is provided by the KeyID Agent Kit MCP server (keyid-ai/agent-kit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.