AI agents call sp_search_read 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 information retrieval only—searching SharePoint and returning file content. It has no side effects on data (no creation, modification, or deletion). However, severity is medium rather than low because: (1) it accesses Microsoft 365 SharePoint documents which may contain sensitive corporate data, and (2) an AI agent could potentially exfiltrate confidential information if given broad search queries…
From the tool's definition Tool name contains 'search_read' and description states 'Search for a file and immediately return its content' with emphasis on finding and reading documents. No modification, deletion, or execution capabilities described.
Attacks that exploit this kind of access
Search for a file and immediately return its content in one step. This is the EASIEST and MOST RELIABLE way to find and read a document. 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 sp_search_read: 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.
sp_search_read 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 sp_search_read 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 sp_search_read. 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.
sp_search_read 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 →