AI agents call fetch_url 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 retrieves data (web page content) without modifying, deleting, or executing operations on target systems. However, severity is medium rather than low because: (1) it uses a headless browser which could be exploited for reconnaissance or to bypass security controls, (2) it accesses arbitrary URLs which could be abused for SSRF attacks, and (3) there is potential for sensitive data exposure depending on what…
From the tool's definition Tool description states 'Retrieve web page content from a specified URL using a headless Chromium browser' - the verb 'Retrieve' and phrase 'web page content' clearly indicate data retrieval with no side effects.
Attacks that exploit this kind of access
Retrieve web page content from a specified URL using a headless Chromium browser. 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_url: 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_url 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_url 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_url. 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_url 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 →