AI agents use create_reply_draft to create or update resources in Mcp Imap — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Imap environment.
This tool creates a new email draft as a reply to an existing message. Creating drafts is a reversible write operation—the draft exists but is not yet sent, so it can be modified, discarded, or deleted without permanent consequences. It does not execute arbitrary code, delete data irreversibly, move money, or read existing messages.
From the tool's definition Tool description states 'Create a reply draft' which creates new email content. The tool description explicitly uses the verb 'Create', indicating it generates and stores new data (a draft email) reversibly—drafts can be deleted or modified before sending.
Attacks that exploit this kind of access
Create a reply draft on an existing email thread. Finds the message by UID, sets In-Reply-To and References headers to keep it in the same thread. It is categorised as a Write tool in the Mcp Imap MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Imap MCP server in PolicyLayer and add a rule for create_reply_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 Mcp Imap. Nothing to install.
create_reply_draft is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_reply_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.
Set action: deny in the PolicyLayer policy for create_reply_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.
create_reply_draft is provided by the Mcp Imap MCP server (ngcdan/mcp-imap-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →