Medium Risk

create_draft

Create a draft email for the user to review and approve before sending. This is the preferred way for AI agents to compose emails - the user can review, edit, and approve drafts from the web dashboard. Drafts expire after 72 hours if not acted on. Rate limited per plan.

Part of the PO6 Mailbox server.

create_draft can modify PO6 Mailbox data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE PO6 MAILBOX →

Free to start. No card required.

AI agents use create_draft to create or modify resources in PO6 Mailbox. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call create_draft repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach PO6 Mailbox.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_draft": {
      "limits": [
        {
          "counter": "create_draft_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full PO6 Mailbox policy for all 39 tools.

Get this rule live on your own PO6 Mailbox server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY PO6 MAILBOX →

View all 39 tools →

These attack patterns abuse exactly the kind of access create_draft gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so create_draft only ever does what you allow.

SECURE PO6 MAILBOX →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the create_draft tool do? +

Create a draft email for the user to review and approve before sending. This is the preferred way for AI agents to compose emails - the user can review, edit, and approve drafts from the web dashboard. Drafts expire after 72 hours if not acted on. Rate limited per plan.. It is categorised as a Write tool in the PO6 Mailbox MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_draft? +

Register the PO6 Mailbox MCP server in PolicyLayer and add a rule for create_draft: 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 PO6 Mailbox. Nothing to install.

What risk level is create_draft? +

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

Can I rate-limit create_draft? +

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

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

create_draft is provided by the PO6 Mailbox MCP server (https://mcp.po6.com). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every PO6 Mailbox tool call.

Deterministic rules across all 39 PO6 Mailbox tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.