Search across multiple Microsoft 365 resources using the modern search API
AI agents call unified_search to retrieve information from Microsoft MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs information retrieval across Microsoft 365 services without creating, modifying, deleting, or executing operations. Search/query operations are inherently Read category with low severity since they do not alter state or trigger external actions. While the scope spans multiple resources and could expose sensitive data if misused, the fundamental action is passive data retrieval.
From the tool's definition Tool description explicitly states 'Search across multiple Microsoft 365 resources' — a query operation with no modification or deletion capability.
Attacks that exploit this kind of access
Search across multiple Microsoft 365 resources using the modern search API. It is categorised as a Read tool in the Microsoft MCP MCP Server, which means it retrieves data without modifying state.
Register the Microsoft MCP server in PolicyLayer and add a rule for unified_search: 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 Microsoft MCP. Nothing to install.
unified_search 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 unified_search 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 unified_search. 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.
unified_search is provided by the Microsoft MCP server (purva-kashyap/microsoft-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 →