Opera brings MCP browser connector to Opera One and Opera GX after Neon-exclusive launch
Opera is extending its MCP-compatible browser connector feature to Opera One and Opera GX, making it available beyond the subscription-based Opera Neon browser. The feature allows AI assistants including Claude, ChatGPT, and Gemini to access browser tabs, read page content, and take screenshots during live browsing sessions.
Opera brings MCP browser connector to Opera One and Opera GX after Neon-exclusive launch
Opera is extending its MCP-compatible browser connector feature to Opera One and Opera GX, ending the exclusivity period that limited the functionality to Opera Neon subscribers since last month.
The browser connector implements the Model Context Protocol (MCP), an open standard that connects AI models to external systems. The feature allows AI assistants including Claude, ChatGPT, and Gemini to access browser tabs, read page content, and take screenshots during live browsing sessions.
From subscription-only to general availability
Opera initially launched MCP compatibility in Opera Neon, its subscription-based agentic browser, in March 2026. That release enabled Neon subscribers to connect external AI tools including ChatGPT, Claude, Lovable, n8n, and OpenClaw directly to their browsing sessions.
The expansion to Opera One and Opera GX removes the subscription requirement, making the feature available to a broader user base.
According to Mohamed Salah, Senior Director of Product at Opera, the rollout reflects the company's focus on user choice, "ensuring users aren't bound to a single company's ecosystem, but are instead free to combine the best tools for their specific needs."
Technical implementation
MCP serves as a connector between AI models (such as ChatGPT, Gemini, and Claude) and external systems (including Notion, Google Drive, Slack, GitHub, and Zapier). In Opera's implementation, the protocol enables AI assistants to:
- Access and read page content from active tabs
- Understand the context of multiple open tabs
- Take screenshots to analyze images and graphs
- Perform actions within the browser session
To enable the feature, users must navigate to Settings, search for AI Services, install Browser Connector, then connect their preferred LLM.
The feature is rolling out today in Early Bird mode for Opera One and Opera GX users.
What this means
Opera's move to standardize on MCP and expand availability beyond a subscription product signals growing industry adoption of interoperability protocols for AI assistants. By supporting multiple AI providers rather than locking users into a proprietary system, Opera positions itself as a neutral platform in the competitive browser AI space. The practical impact depends on whether users find value in granting AI assistants direct browser access—a capability that raises both productivity opportunities and potential privacy considerations.
Related Articles
Anthropic Launches Model Hardware Standard to Let AI Agents Control Lab Robots and Machines
Anthropic has released a research preview of the Model Hardware Standard (MHS), a protocol that lets AI agents discover and control physical devices like robotic arms and liquid handlers through a single interface. Built with HHMI Janelia Research Campus, the spec has been tested by Genentech, Carnegie Mellon, and QuEra, with Anthropic claiming it cuts hardware integration time from weeks to hours.
Google Launches Gemini Enterprise for Legal, Connecting AI to Contract and Research Platforms
Google Cloud has launched Gemini Enterprise for Legal, a preview product that connects its Gemini models to legal software like iManage, DocuSign, Everlaw, RelativityOne, and Harvey via MCP connectors. The tool automates contract review, legal research, and regulatory tracking while respecting existing permission structures.
OpenAI Adds Multi-Account Support for Gmail and Google Calendar in ChatGPT and Codex
OpenAI has enabled ChatGPT and Codex users to connect multiple Gmail, Google Calendar, and Google Contacts accounts to a single plugin, removing a prior one-account limitation. The change was confirmed by OpenAI engineer Gabriel Chua on August 28, 2026.
OpenAI Tests 'Persistent Mode' for Codex, Enabling Always-On AI Agents
OpenAI is developing a 'Persistent Mode' for its Codex agent that keeps the AI running until manually stopped, according to code discovered by WIRED. The feature includes a 'proactivity' capability allowing the agent to generate follow-up tasks and contact users without being asked.
Comments
Loading...