AI agents call read_url_browser to retrieve information from Qsw without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reads web page content via browser automation. While it can access pages behind authentication, it performs no modifications, deletions, or external operations beyond retrieving HTML/rendered content. The capability to handle login states and cookies enables access to more content, but the fundamental operation remains read-only retrieval.
From the tool's definition Tool name 'read_url_browser' and description '使用浏览器读取网页（支持登录状态、Cookie、SPA 页面）' (translates to 'Read web pages using a browser (supporting login state, cookies, SPA pages)'). The verb 'read' and 'reading' indicates data retrieval with no side effects.
Attacks that exploit this kind of access
使用浏览器读取网页（支持登录状态、Cookie、SPA 页面）. It is categorised as a Read tool in the Qsw MCP Server, which means it retrieves data without modifying state.
Register the Qsw MCP server in PolicyLayer and add a rule for read_url_browser: 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 Qsw. Nothing to install.
read_url_browser 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 read_url_browser 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 read_url_browser. 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.
read_url_browser is provided by the Qsw MCP server (qinouz/qsw-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 →