Updates an existing email draft
AI agents use update-draft to create or update resources in Outlook Assistant — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Outlook Assistant environment.
This tool creates or modifies data reversibly by editing draft email content. It does not delete data (which would be Destructive) nor execute arbitrary code (Execute). The severity is medium because misuse could result in modified drafts being sent unintentionally or confidential information being altered, but the impact is limited to email drafts rather than financial transactions or system-wide operations.
From the tool's definition Tool description states it "Updates an existing email draft" which modifies existing data (the draft email content) reversibly without permanent deletion.
Attacks that exploit this kind of access
Updates an existing email draft. It is categorised as a Write tool in the Outlook Assistant MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Outlook Assistant MCP server in PolicyLayer and add a rule for update-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 Outlook Assistant. Nothing to install.
update-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 update-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 update-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.
update-draft is provided by the Outlook Assistant MCP server (titanzero/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 →