
Browser automation MCP: connect AI agents to live Chrome with user context.
Visit Pagerunner — The Browser Layer That LearnsPagerunner is an open-source Model Context Protocol (MCP) server that acts as a browser automation layer for Chrome. It allows AI agents such as Claude (and any client that supports MCP) to interact with a live Chrome session using your existing browser profiles—including access to cookies, saved passwords, and browsing history. Pagerunner provides a comprehensive automation and scripting toolkit, including navigation, page interactions (click, type, fill, scroll), screenshots, JavaScript execution, tab management, data extraction, and session state management, all controllable via the MCP protocol. Site intelligence features allow agents to adapt by registering JS adapters, reusing site authentication, and automating workflows securely across web environments. Pagerunner is ideal for AI/agent developers, automation engineers, and power users who want to create intelligent, context-aware browser automations integrated with real user data.
Visit Pagerunner — The Browser Layer That Learns's official website for product details and getting started.
Comprehensive guides and references for using Pagerunner effectively.
Engage with other users and developers to share insights and troubleshoot issues.