Lists mail folders in your Outlook account
AI agents call list-folders to retrieve information from Outlook MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation that queries and returns folder metadata from Outlook. It has no side effects, does not modify data, and does not execute external operations or trigger irreversible changes. The blast radius is minimal—an agent misusing this tool could discover folder names but cannot access or alter email contents or account settings.
From the tool's definition Tool name 'list-folders' and description 'Lists mail folders in your Outlook account' indicate a query operation that retrieves folder structure without modification or execution.
Attacks that exploit this kind of access
Lists mail folders in your Outlook account. It is categorised as a Read tool in the Outlook MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Outlook MCP Server MCP server in PolicyLayer and add a rule for list-folders: 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 MCP Server. Nothing to install.
list-folders is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list-folders 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 list-folders. 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.
list-folders is provided by the Outlook MCP Server MCP server (peacockery-studio/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 →