AI agents call get_ntp_config 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.
The tool name begins with 'get_', which is a standard pattern for read operations across this MCP server. It retrieves NTP configuration settings from an AD environment. Even though the description is empty, the consistent naming pattern with other acknowledged read tools (get_computers, get_dc_*) and the absence of action verbs suggesting modification (create, update, delete, execute) indicate this is a read-only…
From the tool's definition Tool name 'get_ntp_config' follows the 'get_*' pattern consistent with sibling tools like 'get_computers', 'get_dc_features', 'get_dc_file_locations', 'get_dc_network_config', 'get_dc_services', and 'get_dc_software'.
Attacks that exploit this kind of access
get_ntp_config. 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_ntp_config: 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_ntp_config 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_ntp_config 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_ntp_config. 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_ntp_config 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 →