Update email properties (isRead, categories, flag, etc.)
AI agents use update_email to create or update resources in Microsoft MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Microsoft MCP environment.
This tool modifies email attributes (read status, categories, flags) which are changeable, reversible operations. It does not delete emails (which would be Destructive) or move money (Financial). It performs Write-class operations on existing email records.
From the tool's definition Tool name is 'update_email' and description states it 'Update[s] email properties (isRead, categories, flag, etc.)' — these are reversible modifications to email metadata and state without deletion or message body changes.
Attacks that exploit this kind of access
Update email properties (isRead, categories, flag, etc.). It is categorised as a Write tool in the Microsoft MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Microsoft MCP server in PolicyLayer and add a rule for update_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 Microsoft MCP. Nothing to install.
update_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 update_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 update_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.
update_email is provided by the Microsoft MCP server (purva-kashyap/microsoft-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 →