AI agents call get_user_by_name to retrieve information from LegacyMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query of Active Directory to fetch a user record by identifier. It retrieves existing data with no side effects, creation, deletion, or modification capability. While it may expose sensitive directory information, the tool itself is purely informational.
From the tool's definition Tool name 'get_user_by_name' and description 'Return the full record for a single user looked up by SamAccountName' indicate a query/lookup operation that retrieves data without modification.
Attacks that exploit this kind of access
Return the full record for a single user looked up by SamAccountName. It is categorised as a Read tool in the LegacyMCP MCP Server, which means it retrieves data without modifying state.
Register the Legacy MCP server in PolicyLayer and add a rule for get_user_by_name: 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 LegacyMCP. Nothing to install.
get_user_by_name 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 get_user_by_name 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 get_user_by_name. 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.
get_user_by_name is provided by the Legacy MCP server (marco-lelli/legacy-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 →