AI agents call fetch_urls to retrieve information from Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches and returns data from web pages using a headless browser. There is no indication it modifies, deletes, executes arbitrary code, or performs financial transactions. The parallel fetching with a shared browser context is an implementation detail that doesn't change the fundamental nature of the operation as a read-only retrieval.
From the tool's definition Tool description states 'Retrieve web page content' which is a data retrieval operation with no side effects. The verb 'Retrieve' and the context of 'web page content' clearly indicate a read-only operation.
Attacks that exploit this kind of access
Retrieve web page content from multiple URLs in parallel using a shared headless Chromium browser context. It is categorised as a Read tool in the Server MCP Server, which means it retrieves data without modifying state.
Register the Server MCP server in PolicyLayer and add a rule for fetch_urls: 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 Server. Nothing to install.
fetch_urls 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 fetch_urls 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 fetch_urls. 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.
fetch_urls is provided by the Server MCP server (@nest-mcp/server). 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 →