Show HN: Drive your real logged-in Chrome from Claude Code and Codex (MCP) (github.com)

A new tool called Browser Bridge has been introduced that allows AI agents, such as Claude Code and OpenAI Codex, to drive a user's real, logged-in Chrome browser using the Model Context Protocol (MCP). This innovative approach eliminates the need for headless browsing or multiple logins, enabling the agents to access current sessions seamlessly. Users can instruct the AI to perform tasks like summarizing a feed or monitoring API traffic within authenticated applications, thus enhancing the efficiency of routine browsing and development tasks. This advancement is significant for the AI and machine learning landscape as it represents a new paradigm in human-computer interaction, allowing for more nuanced and context-aware interactions via AI. The Browser Bridge tool supports a variety of features, including session recording, web security testing, and a toolkit that spans 63 different utilities. By integrating directly with existing logged-in browser sessions, this solution not only improves user experience but also opens up new possibilities for automating and optimizing workflows in web development and data analysis, blurring the lines between passive usage and active AI assistance.