AI agents call od_shared_with_me 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 a query operation to list shared files accessible to the authenticated user. It has no side effects—it retrieves data only and does not create, modify, delete, or execute any operations. The blast radius of misuse is minimal; an attacker could discover what files have been shared with a user, but cannot access file contents, modify them, delete them, or move money.
From the tool's definition Tool name 'od_shared_with_me' and description 'List files that others have shared with you via OneDrive' indicate a read-only operation that retrieves and enumerates shared files without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
List files that others have shared with you via OneDrive. 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_shared_with_me: 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_shared_with_me 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_shared_with_me 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_shared_with_me. 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_shared_with_me 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 →