Search for users by display name or email
AI agents call search_user to retrieve information from Microsoft Graph MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search/query operation to retrieve user data. It has no side effects—it does not create, modify, delete, or execute actions on users or other resources. It is a straightforward read operation consistent with the Read category. Severity is low because searching user directories is a common administrative function with minimal blast radius if misused by an agent.
From the tool's definition Tool name 'search_user' and description 'Search for users by display name or email' indicate a query operation that retrieves user information without modifying or deleting data.
Attacks that exploit this kind of access
Search for users by display name or email. It is categorised as a Read tool in the Microsoft Graph MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Microsoft Graph MCP Server MCP server in PolicyLayer and add a rule for search_user: 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 Graph MCP Server. Nothing to install.
search_user 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 search_user 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 search_user. 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.
search_user is provided by the Microsoft Graph MCP Server MCP server (ry-ops/microsoft-graph-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 →