An MCP server that runs in the browser, letting web pages register custom tools and prompts and expose them to an MCP client over WebSocket. Enables agents to drive UI, call page-scoped APIs, and get human-in-the-loop confirmation.
Lets an AI share the same live browser tab as a person, receiving the user's Alt+click target and enabling the AI to inspect, click, fill, type, navigate, or otherwise operate on that real page. It runs locally and pairs with the browser extension to bridge the user's page to the MCP client.
Enables remote AI agents to control a local, authenticated desktop browser over MCP through an outbound WebSocket bridge and Chrome extension, supporting tab management, navigation, page reading, clicking, typing, scrolling, screenshots, and JavaScript evaluation.
Turns a logged-in ChatGPT Web conversation into an OpenAI-compatible HTTP endpoint, letting any compatible client send chat completions and responses without an API key. Native tool calls tunnel back to the local MCP server and execute under bubblewrap sandboxing with capability-bound session tokens, idempotent turns, and DOM-captured answers.