draft_email · Nexus Core MCP: Risk & Policy

WHAT IT DOES

What draft_email does on Nexus Core

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

WHY IT NEEDS A POLICY

Why draft_email needs a policy

This tool creates a new email draft in Gmail without sending it, which is a reversible modification operation. It does not execute code, delete data, or move money. The severity is medium because while drafts can be deleted, if an AI agent maliciously creates many drafts or composes sensitive/harmful content in draft form, it could cause disruption or expose private information.

From the tool's definition Create a Gmail draft. Returns draft_id. The tool creates a new email draft, which is reversible by deletion, and does not send or permanently modify existing data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

draft_email Rate-limited

draft_email 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": {
    "draft_email": {
      "limits": [
        {
          "counter": "draft_email_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 Nexus Core, so you can run agents against it safely.

FAQ

Questions about draft_email

What does the draft_email tool do? +

Create a Gmail draft. Returns draft_id. It is categorised as a Write tool in the Nexus Core MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on draft_email? +

Register the Nexus Core MCP server in PolicyLayer and add a rule for draft_email: 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 Nexus Core. Nothing to install.

What risk level is draft_email? +

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

Can I rate-limit draft_email? +

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

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

draft_email is provided by the Nexus Core MCP server (noumenon-ai/nexus-core). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.