Mark an email as read or unread
AI agents use outlook_mark_as_read to create or update resources in Outlook — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Outlook environment.
This tool changes email metadata (the read status) but does not delete, create new messages, execute code, or move money. It is reversible (can toggle between read and unread), making it a Write operation. The severity is low because the change is limited to a single email's status flag with minimal blast radius and can be easily undone.
From the tool's definition Tool description states 'Mark an email as read or unread' — this modifies the read/unread status flag of an email message, which is a metadata state change.
Documented attack patterns abuse exactly the kind of access outlook_mark_as_read gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Outlook, and nothing reaches the server without passing your rules. This is the rule we recommend for outlook_mark_as_read:
{
"version": "1",
"default": "deny",
"tools": {
"outlook_mark_as_read": {
"limits": [
{
"counter": "outlook_mark_as_read_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}outlook_mark_as_read stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Mark an email as read or unread. It is categorised as a Write tool in the Outlook MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Outlook MCP server in PolicyLayer and add a rule for outlook_mark_as_read: 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. Nothing to install.
outlook_mark_as_read 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 outlook_mark_as_read 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 outlook_mark_as_read. 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.
outlook_mark_as_read is provided by the Outlook MCP server (xenoxilus/outlook-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Outlook, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
43 Outlook tools catalogued and risk-classified — across an index of 43,000+ MCP servers.