AI agents call od_list_files to retrieve information from M365 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs only directory listing/browsing operations on OneDrive. It retrieves information about files and folders but does not create, modify, delete, or execute any resources. The optional item_id parameter allows navigation to subfolders but does not change any data.
From the tool's definition Tool name 'od_list_files' and description 'List files and folders in your personal OneDrive' indicate a read-only operation that retrieves and displays file/folder metadata without modifying, deleting, or executing any data.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
List files and folders in your personal OneDrive. Omit item_id for root folder, or provide a folder ID to browse subfolders. It is categorised as a Read tool in the M365 MCP Server, which means it retrieves data without modifying state.
Register the M365 MCP server in PolicyLayer and add a rule for od_list_files: 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.
od_list_files 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 od_list_files 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 od_list_files. 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.
od_list_files is provided by the M365 MCP server (swamirama/m365-mcp-server). 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 →