Create a draft email for later editing and sending.
AI agents use keyid_create_draft 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.
This tool creates email drafts, which modifies data in the email system reversibly. Drafts can be edited or deleted before sending, making this a Write operation rather than Execute or Destructive. The severity is medium because a compromised agent could create numerous spam/phishing draft emails or impersonate the account holder, though the drafts are not immediately sent (limiting immediate blast radius).
From the tool's definition Tool name is 'keyid_create_draft' and description states it will 'Create a draft email for later editing and sending.' This creates (but does not send) email message data.
Attacks that exploit this kind of access
Create a draft email for later editing and sending. 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.
Register the KeyID Agent Kit MCP server in PolicyLayer and add a rule for keyid_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 KeyID Agent Kit. Nothing to install.
keyid_create_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 keyid_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.
Set action: deny in the PolicyLayer policy for keyid_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.
keyid_create_draft 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.
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 →