Manage emails with multiple actions. Supports moving, deleting, archiving, flagging, and categorizing emails. Actions include: move_single, move_all, delete_single, delete_multiple, delete_all, archive_single, archive_multiple, flag_single, flag_multiple, categorize_single, categorize_multiple. R...
AI agents call manage_emails to permanently remove resources in Microsoft Graph MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool includes irreversible deletion actions (delete_single, delete_multiple, delete_all) that can permanently remove emails. The 'delete_all' action in particular has a massive blast radius — an AI agent misusing this could wipe an entire mailbox. Deletion of emails is generally irreversible without backup recovery, placing this firmly in Destructive.
From the tool's definition Supports moving, deleting, archiving, flagging, and categorizing emails. Actions include: move_single, move_all, delete_single, delete_multiple, delete_all, archive_single, archive_multiple
Documented attack patterns abuse exactly the kind of access manage_emails gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Microsoft Graph MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for manage_emails:
{
"version": "1",
"default": "deny",
"hide": [
"manage_emails"
]
}manage_emails disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Manage emails with multiple actions. Supports moving, deleting, archiving, flagging, and categorizing emails. Actions include: move_single, move_all, delete_single, delete_multiple, delete_all, archive_single, archive_multiple, flag_single, flag_multiple, categorize_single, categorize_multiple. Returns: {success: boolean, message: string, moved_count: integer, failed_count: integer, errors: array}. Note: Invalid cache_number returns appropriate error message. It is categorised as a Destructive tool in the Microsoft Graph MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Microsoft Graph MCP Server MCP server in PolicyLayer and add a rule for manage_emails: 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 Graph MCP Server. Nothing to install.
manage_emails is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the manage_emails 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 manage_emails. 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.
manage_emails is provided by the Microsoft Graph MCP Server MCP server (marlonluo2018/microsoft_graph_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Microsoft Graph MCP Server, 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.
19 Microsoft Graph MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.