AI agents call od_get_file 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 retrieves and parses file content without modifying, deleting, or executing anything. It is a straightforward read operation on personal cloud storage. The severity is low because misuse would only expose the user's own files to the AI, with no ability to affect other systems, users, or data integrity. Confidence is high due to the clear read-only semantics in the description.
From the tool's definition Tool description states 'Get a file from your personal OneDrive by item_id' with automatic parsing of document contents to readable text. No modification, deletion, or execution capability is described.
Attacks that exploit this kind of access
Get a file from your personal OneDrive by item_id. PDF, Word (.docx), Excel (.xlsx), PowerPoint (.pptx) are auto-parsed to readable text. Max 20MB. 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_get_file: 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_get_file 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_get_file 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_get_file. 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_get_file 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 →