AI agents call get_default_password_policy 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 queries and returns existing Active Directory password policy configuration data. It performs a read-only operation on domain policy objects without creating, modifying, deleting, or executing any changes. The severity is low because viewing password policy settings, while potentially informative to an attacker about security posture, does not directly compromise systems or data on its own.
From the tool's definition Tool name 'get_default_password_policy' and description 'Return the Default Domain Password Policy for a given domain' indicate a retrieval operation with no modifications or side effects.
Attacks that exploit this kind of access
Return the Default Domain Password Policy for a given domain,. 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_default_password_policy: 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_default_password_policy 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_default_password_policy 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_default_password_policy. 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_default_password_policy 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 →