AI-native browser automation CLI and MCP server for Chrome. 90+ commands. Works with Claude Code, Cursor, Copilot, and 6 more.
# testmu-browser-agent AI-native browser automation CLI and MCP server for Chrome, built in Go. [](https://github.com/4DvAnCeBoY/testmu-browser-agent-public/actions) [](https://go.dev/) [](https://github.com/4DvAnCeBoY/testmu-browser-agent-public/releases) ### Works with your AI coding tool | Claude Code | Cursor | GitHub Copilot | Windsurf | Cursor CLI | Codex | Goose | OpenCode | Cline | |:-----------:|:------:|:--------------:|:--------:|:----------:|:-----:|:-----:|:--------:|:-----:| | [Setup](plugins/claude-code/) | [Setup](plugins/cursor/) | [Setup](plugins/cursor/) | [Setup](plugins/windsurf/) | [Setup](plugins/cursor-cli/) | [Setup](plugins/codex/) | [Setup](plugins/goose/) | [Setup](plugins/opencode/) | [Setup](plugins/cline/) | > Works with any agent that can run shell commands or connect via MCP. [Auto-install all plugins](scripts/install-plugins.sh) with one script. --- 68+ CLI commands. 10 MCP tools. 90+ total actions. Stable `@ref` element IDs. Single binary. Zero dependencies. --- ## What is testmu-browser-agent? testmu-browser-agent is a single Go binary that exposes browser automation through three surfaces: a 68+ command CLI, a 10-tool MCP server for Claude Code, and a REST/SSE daemon API — 90+ total actions. - **68+ CLI commands** — navigate, click, fill, screenshot, network interception, auth vault, device emulation, video recording, HAR capture, and more, all from the terminal - **22 CDP actions** — advanced diagnostics, security, and performance actions available via MCP tools and REST API - **MCP server with 10 tools** — plug directly into Claude Code so AI agents can control the browser without any additional setup - **Accessibility snapshots with `@ref` IDs** — token-effici
Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.