Scan network and return only newly discovered devices since last scan.
AI agents call detect_new_devices to retrieve information from Network Scanner MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries network state (newly discovered devices) without creating, modifying, or deleting any data. It has no side effects beyond gathering information about network infrastructure.
From the tool's definition Tool performs network scanning and device discovery with no modification capabilities. Description: 'Scan network and return only newly discovered devices since last scan.' The action is detection/discovery, a read-only operation.
Attacks that exploit this kind of access
Scan network and return only newly discovered devices since last scan. It is categorised as a Read tool in the Network Scanner MCP MCP Server, which means it retrieves data without modifying state.
Register the Network Scanner MCP server in PolicyLayer and add a rule for detect_new_devices: 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 Network Scanner MCP. Nothing to install.
detect_new_devices 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 detect_new_devices 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 detect_new_devices. 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.
detect_new_devices is provided by the Network Scanner MCP server (marc-shade/network-scanner-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 →