导航到指定URL
AI agents invoke navigate_to_page to trigger actions in MCP Browser Text Reader. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Navigation is an Execute action because it triggers external browser operations whose effects depend on the URL argument. While read-only in isolation, navigating to arbitrary URLs controlled by an AI agent creates severe risk: the browser will execute JavaScript, load remote content, and potentially trigger drive-by downloads or credential theft.
From the tool's definition Tool navigates to arbitrary URLs by controlling a real Chrome browser. Description states it 'Controls a real Chrome browser to navigate web pages' and this tool performs that navigation action.
Attacks that exploit this kind of access
导航到指定URL. It is categorised as a Execute tool in the MCP Browser Text Reader MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Browser Text Reader MCP server in PolicyLayer and add a rule for navigate_to_page: 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 MCP Browser Text Reader. Nothing to install.
navigate_to_page is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the navigate_to_page 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 navigate_to_page. 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.
navigate_to_page is provided by the MCP Browser Text Reader MCP server (tikous/mymcp). 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 →