Return network requests captured in the tab since page load: fetch & XHR (with method, status, type, timing, and capped response bodies) plus browser-loaded resources (image/css/script/font — metadata only).
AI agents call network_calls to retrieve information from Nextjs Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical network traffic data from a running browser tab for inspection and debugging purposes. It has no side effects on the application state, data, or external systems. The 'capped response bodies' and metadata-only approach further confirm read-only semantics.
From the tool's definition Tool description states it 'Return[s] network requests captured in the tab since page load' — a passive inspection/query operation with 'method, status, type, timing, and capped response bodies' and 'metadata only' for browser resources.
Attacks that exploit this kind of access
Return network requests captured in the tab since page load: fetch & XHR (with method, status, type, timing, and capped response bodies) plus browser-loaded resources (image/css/script/font — metadata only). It is categorised as a Read tool in the Nextjs Agent MCP Server, which means it retrieves data without modifying state.
Register the Nextjs Agent MCP server in PolicyLayer and add a rule for network_calls: 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 Nextjs Agent. Nothing to install.
network_calls 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 network_calls 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 network_calls. 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.
network_calls is provided by the Nextjs Agent MCP server (zohaib3249/nextjs-agent-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 →