AI agents call file_get 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.
The 'file_get' tool name follows the standard pattern for retrieval operations (get, fetch, retrieve). Within a Microsoft 365 context managing OneDrive files, this almost certainly retrieves or queries file data. Without description text, confidence is moderate, but the naming convention and sibling tool patterns (calendar_check_availability, account_list using descriptive verbs) indicate read-only retrieval.
From the tool's definition Tool name 'file_get' with no description; based on naming convention and context in m365-mcp server managing OneDrive and file services, 'get' operations typically retrieve data without modification. The empty description limits certainty.
Attacks that exploit this kind of access
file_get. 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 file_get: 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.
file_get 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 file_get 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 file_get. 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.
file_get is provided by the M365 MCP server (robin-collins/m365-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 →