AI agents call get_sites 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 retrieves Active Directory infrastructure data (sites, subnets, and domain controllers). While it is non-destructive and non-modifying, the information returned includes sensitive network topology and infrastructure details that could enable reconnaissance or attack planning if misused by an AI agent.
From the tool's definition Tool name and description indicate data retrieval: 'Return all AD sites with their associated subnets and DCs.' The verb 'Return' and the read-only nature of querying AD site information confirm this is a Read operation with no side effects.
Attacks that exploit this kind of access
Return all AD sites with their associated subnets and DCs. 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_sites: 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_sites 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_sites 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_sites. 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_sites 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 →