AI agents call ms_sharepoint to retrieve information from M365 MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs information retrieval and browsing operations only: searching sites, listing metadata, and browsing items. It has no capability to modify, delete, or execute actions. The read-only nature and limited blast radius from accidental misuse justify a low severity classification.
From the tool's definition Tool description explicitly states 'Search SharePoint sites, list site lists, or browse list items' — all read-only operations. Server description confirms 'read-only access'. No create, modify, delete, or execute capabilities mentioned.
Attacks that exploit this kind of access
Search SharePoint sites, list site lists, or browse list items. Without parameters, searches all accessible sites. Provide site_id to see its lists, or site_id + list_id to browse items. It is categorised as a Read tool in the M365 MCP MCP Server, which means it retrieves data without modifying state.
Register the M365 MCP server in PolicyLayer and add a rule for ms_sharepoint: 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 MCP. Nothing to install.
ms_sharepoint 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 ms_sharepoint 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 ms_sharepoint. 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.
ms_sharepoint is provided by the M365 MCP server (stumason/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 →