Opera (NASDAQ:OPRA) has unveiled a new MCP Connector for its Opera Neon browser, allowing external artificial intelligence tools to connect directly to the browser and perform actions within a user’s active browsing session.
According to the Norwegian browser developer, the connector allows AI platforms such as Claude, ChatGPT, Lovable, n8n, and OpenClaw to access real-time web context and carry out tasks inside the browser environment rather than functioning independently.
Through the Model Context Protocol (MCP) endpoint, connected AI systems can view browser information including open tabs, page content, and authenticated sessions. The integration also enables AI clients to perform tasks such as navigating websites, extracting information, taking screenshots, completing forms, opening new tabs, and conducting searches.
“Last year, we launched Browser Operator as a first step toward an agentic browser. Now we are opening those capabilities to external AI clients through MCP, so they can act directly inside the browser, not outside it,” said Monika Kurczyńska, Director of R&D for browser AI at Opera.
Opera said the new feature is designed to eliminate workflow disruptions that occur when users must copy content between browser tabs or repeatedly provide context when switching between AI tools and web pages.
To safeguard user sessions, the company implemented a secure MCP server URL authorization system that controls how AI clients access browser activity. A persistent proxy layer helps maintain connection stability and provides status updates if the browser becomes temporarily unavailable.
The MCP Connector builds on Opera Neon’s existing capabilities for executing browser-based actions. The company highlighted potential use cases including software development testing, design prototyping, and workflow automation.
The feature is currently available to Opera Neon subscribers, while Opera plans to roll out a simplified version of the connector in its main Opera One and Opera GX browsers in the future.