create_draft_email
AI agents use create_draft_email to create or update resources in MCP Outlook — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Outlook environment.
Creating a draft email is a reversible write operation—it stores new data (an unsent email) that can be modified or deleted. It does not send the email or trigger immediate side effects like Execute or Destructive tools would.
From the tool's definition Tool name 'create_draft_email' and the context of the MCP Outlook server which manages emails. The description is empty, but the name and sibling tools (create_calendar_event, create_contact, download_email_attachment, get_calendar_events, etc.) indicate this…
Attacks that exploit this kind of access
create_draft_email. It is categorised as a Write tool in the MCP Outlook MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Outlook MCP server in PolicyLayer and add a rule for create_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 MCP Outlook. Nothing to install.
create_draft_email 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_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.
Set action: deny in the PolicyLayer policy for create_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.
create_draft_email is provided by the MCP Outlook MCP server (vince1024/outlook-mcp). 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 →