AI agents use emailrules_create to create or update resources in M365 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your M365 environment.
Email rules creation is a reversible Write operation—new rules can be modified or deleted. It does not delete data (not Destructive), execute arbitrary code (not Execute), or move money (not Financial). However, email rules can significantly impact email routing, filtering, and visibility, affecting multiple mailboxes if misconfigured by an agent, justifying medium severity.
From the tool's definition Tool name 'emailrules_create' indicates creation of email rules within Microsoft 365/Outlook. The '_create' suffix and context of email management systems shows this tool creates new rule objects that modify email handling behavior.
Attacks that exploit this kind of access
emailrules_create. It is categorised as a Write tool in the M365 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the M365 MCP server in PolicyLayer and add a rule for emailrules_create: 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 M365. Nothing to install.
emailrules_create 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 emailrules_create 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 emailrules_create. 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.
emailrules_create is provided by the M365 MCP server (robin-collins/m365-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 →