Opera has launched an MCP Connector for its Neon browser, allowing third‑party AI agents such as ChatGPT, Claude, n8n, Lovable and OpenClaw to directly interact with the browser. Built on the Model Context Protocol (MCP) created by Anthropic, the feature gives these AI tools real‑time visibility of the screen and the ability to execute browsing tasks, effectively turning Neon into an autonomous agent. The connector is currently available to paid Neon users, with plans to extend a simpler version to other Opera browsers. This move positions Opera at the forefront of AI‑driven browsing. Read more →

OpenAI has added plugin support to its Codex coding assistant, a move aimed at narrowing the functional gap with rival AI coding tools from Anthropic and Google. The new plugins are packaged bundles that may contain skills, app integrations, and Model Context Protocol (MCP) servers, letting users configure Codex for specific tasks with a single click. While power users could already achieve similar results through custom instructions and MCP servers, the plugin library—featuring integrations such as GitHub, Gmail, Box, Cloudflare, and Vercel—offers a more streamlined, searchable experience. Read more →

Google has added a feature to Gemini that allows users to import conversation history from other AI assistants. By copying a response from the previous AI or uploading a ZIP file of exported data, Gemini can continue a discussion without the user having to repeat prior details. The process is available through the Settings menu on the desktop version and supports files up to 5GB. Early testers report smoother interactions despite a brief processing wait, marking a notable step toward seamless multi‑AI workflows. Read more →