连接到浏览器的 DevTools Protocol。支持 Chrome 和 Firefox。\n\nChrome 启动方式:\nWindows: chrome.exe --remote-debugging-port=9222\nmacOS: /Applications/Google\\ Chrome.app/Contents/MacOS/Google\\ Chrome --remote-debugging-port=9222\nLinux: google-chrome --remote-debugging-port=9222\n\nFirefox 启动方式:\nWindows: fire...
AI agents invoke connect_browser to trigger actions in MCP Browser Logger. 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.
Establishing a DevTools Protocol connection to a browser grants the ability to monitor, inspect, and control browser behavior. This is an enabling action for subsequent Execute-level operations (e.g., evaluate_javascript, monitor network traffic). While the connection itself doesn't directly execute code, it triggers an external operation that opens a privileged control channel to the browser.
From the tool's definition 连接到浏览器的 DevTools Protocol (Connect to browser's DevTools Protocol)
Attacks that exploit this kind of access
连接到浏览器的 DevTools Protocol。支持 Chrome 和 Firefox。\n\nChrome 启动方式:\nWindows: chrome.exe --remote-debugging-port=9222\nmacOS: /Applications/Google\\ Chrome.app/Contents/MacOS/Google\\ Chrome --remote-debugging-port=9222\nLinux: google-chrome --remote-debugging-port=9222\n\nFirefox 启动方式:\nWindows: firefox.exe --start-debugger-server 6000\nmacOS: /Applications/Firefox.app/Contents/MacOS/firefox --start-debugger-server 6000\nLinux: firefox --start-debugger-server 6000. It is categorised as a Execute tool in the MCP Browser Logger MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Browser Logger MCP server in PolicyLayer and add a rule for connect_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 MCP Browser Logger. Nothing to install.
connect_browser 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 connect_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 connect_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.
connect_browser is provided by the MCP Browser Logger MCP server (tao-lionel/mcp-browser-logger). 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 →