Turn real Chrome into an MCP-native AI execution layer.
Tabrix is a Chrome extension + local native server that lets any MCP client operate your daily browser session safely and efficiently, with your existing logins, cookies, and browsing context.
Built for the new generation of AI assistants that need to work in the browser users already trust every day.
- Reuse the real logged-in Chrome session instead of rebuilding a fresh browser runtime
- Connect through both
Streamable HTTPandstdio, depending on the MCP host - Stay local-first, while still supporting token-protected remote access over LAN
Documentation: English | Chinese
Tabrix does not spin up "yet another browser." It upgrades your current Chrome into an AI-executable runtime.
- Real session, ready instantly: keep your existing logins, cookies, extensions, and tabs without rebuilding environments
- More stable and safer runtime path: extension + Native Messaging, without keeping
--remote-debugging-portexposed - Remote-ready access: built-in Bearer auth, token management, and token TTL controls for LAN exposure
- Broad client compatibility: works with Claude Desktop, Cursor, Claude Code CLI, Codex CLI, Cherry Studio, Windsurf, Dify, and similar MCP clients
- Local-first architecture: browser state and data stay on your machine by default for stronger privacy and compliance control
- Production operations built in:
tabrix status/doctor --fix/smoke/report
Many browser automation tools start from a fresh runtime. Tabrix starts from the browser your team already uses.
- No login rebuild loop: keep the authenticated tabs, cookies, and extensions you already rely on
- Better fit for real back-office work: operate CMS, ticketing, CRM, support, and ops systems inside the actual browser profile
- Better fit for AI assistants: let Codex, Claude Desktop, Cursor, Cline, and similar clients call into a browser that already has useful context
If your workflow depends on a real logged-in browser, the difference is immediate:
| Fresh browser runtime | Tabrix |
|---|---|
| Rebuild login and cookies again | Reuse the browser session you already have |
| Start from blank tabs and blank context | Start from real tabs, extensions, and live operator context |
| Often optimized for isolated automation runs | Optimized for AI assistants working with a user's daily browser |
| Browser control alone is not enough for ops trust | Add status, doctor, smoke, and recovery around the control path |
- More reliable compliant collection: real-session reuse reduces failures from fresh environments and blank fingerprints
- Higher back-office automation efficiency: automate logged-in CMS, ticketing, and operations workflows with fewer repetitive clicks
- Better team collaboration: secure LAN remote access lets multiple MCP clients call the same browser capability
- Faster regression troubleshooting:
doctor --fixandsmokequickly pinpoint connection-path issues and shorten resolution time
- Browser copilots for research, QA, operations, and support
- Cross-tab task automation with semantic context
- Safe web workflows with human-in-the-loop checkpoints
- MCP toolchains that combine browser, filesystem, and APIs
One realistic first-success path:
- Keep your normal Chrome profile open with the pages you already use
- Install
@tabrix/tabrix, load the extension, and clickConnect - Add Tabrix to Codex, Claude Desktop, Cursor, or another MCP client
- Ask the assistant to inspect the current page, list interactive elements, or navigate the next step
- Reuse the same browser session for follow-up clicks, fills, screenshots, and checks
The first win should feel like "my assistant can finally use my real browser," not "I set up another automation sandbox."
npm install -g @tabrix/tabrix@latest
# or
pnpm install -g @tabrix/tabrix@latestTabrix installation and browser readiness are now treated separately:
- CLI install can succeed even if Chrome/Chromium is not installed yet
- Browser automation becomes ready after
tabrix register,tabrix setup, ortabrix doctor --fixdetects a supported browser executable - The detected browser path is persisted and reused for later auto-launch
If pnpm does not run postinstall scripts:
tabrix registerDownload from Releases, then load the tabrix-extension-vX.Y.Z.zip unpacked folder at chrome://extensions.
After loading, open the extension popup and click Connect once.
Check runtime status:
tabrix statusRun automatic recovery:
tabrix doctor --fixWhat to look for:
tabrix doctor --jsonnow includesbrowser.executable- If Chrome/Chromium is ready, Tabrix persists the resolved path for later browser auto-launch
- If no supported browser is detected, Tabrix stays installed but reports browser automation as not ready
Tabrix currently supports both MCP mainline transports:
Streamable HTTP: default local and remote pathstdio: for CLI hosts or clients that only support stdio
{
"mcpServers": {
"tabrix": {
"type": "streamableHttp",
"url": "http://127.0.0.1:12306/mcp"
}
}
}{
"mcpServers": {
"tabrix": {
"command": "tabrix-stdio"
}
}
}Configs for popular MCP clients (Claude Desktop, Cursor, Claude Code CLI, Codex CLI, Cherry Studio, Windsurf, Dify, etc.): Client Config Quick Reference
Typical remote MCP config:
{
"mcpServers": {
"tabrix": {
"url": "http://<LAN_IP>:12306/mcp",
"headers": {
"Authorization": "Bearer <YOUR_TABRIX_TOKEN>"
}
}
}
}Turn on Remote Access in extension popup and expose:
http://<LAN_IP>:12306/mcp
- Open extension popup -> switch to
Remote-> enableRemote Access - Open
Token Managementand copy current token (or click refresh) - Paste LAN config to your MCP client and start remote automation
- Remote mode must use bearer-token authentication
- Extension
Token Managementpage supports view/copy/refresh - Token validity is configurable:
- Set custom days in
Token Management->Refresh Token - Or set
MCP_AUTH_TOKEN_TTL(0means never expire)
- Set custom days in
- If
MCP_AUTH_TOKENenv is set, env token always has priority
- Browser navigation and tab/window control
- Page interaction (click, fill, keyboard, upload)
- Rich extraction (web content, interactive elements, console)
- Network capture and request replay helpers
- Screenshot, GIF recording, performance trace analysis
- Bookmarks/history operations and JavaScript execution
Installed executables:
tabrix
tabrix-stdioFirst-time guided setup:
tabrix setupRegister Native Messaging host:
tabrix registerFix local execution permissions:
tabrix fix-permissionsUpdate MCP port:
tabrix update-port <port>Check current runtime status:
tabrix statusShow current MCP client config:
tabrix configDiagnose issues (--fix applies common auto-fixes):
tabrix doctortabrix doctor --fixInspect active MCP clients and recent sessions:
tabrix clientsRun browser-path smoke test:
tabrix smokeNeed an isolated browser window for smoke:
tabrix smoke --separate-windowRun stdio-only smoke test:
tabrix stdio-smokeExport diagnostics report (copy to clipboard):
tabrix report --copyDaemon lifecycle commands:
tabrix daemon starttabrix daemon statustabrix daemon stopFull command reference: CLI.md
Full tool list: TOOLS API (EN) | TOOLS API (ZH)
Tabrix is aiming to become a top-tier browser automation execution layer for AI assistants. The roadmap stays public, but we keep it grounded in what the current codebase can realistically absorb next.
- Now: make real-Chrome MCP access more reliable across
Streamable HTTP,stdio, reconnects, and diagnostics - Next: ship structured page snapshots, browser auto-recovery, and stronger real-browser E2E coverage
- Later: add URL Experience Memory, replay artifacts, and richer team collaboration workflows
Read the full public roadmap: ROADMAP.md
Contributions are welcome from both first-time contributors and maintainers.
- Start here: Contributing Guide
- Good first issues: Start with beginner-friendly tasks
- Community discussions: GitHub Discussions
- Architecture: ARCHITECTURE.md
- Security model: SECURITY.md
- Error codes: ERROR_CODES.md
- Reliability and reconnect stability
- Tool schema consistency and DX
- Cross-platform install and packaging quality
- Benchmarking and regression test coverage
Our current priority is community growth and project reputation:
- Lower onboarding friction for new users and contributors
- Keep release quality high with transparent changelogs and issue triage
- Improve reliability across platforms and MCP clients
- Build an open roadmap with active maintainer feedback
Long-term, once adoption and ecosystem maturity are in place, we may explore sustainable paths that remain compatible with the open-source community.
Tabrix is a community-driven continuation of
hangwin/mcp-chrome.
We appreciate the original maintainers and contributors who created the foundation. Tabrix exists to provide sustained maintenance, clearer roadmap execution, and faster iteration.
- CLI Commands
- Stable Quickstart
- Transport Modes (Streamable HTTP / stdio)
- Popup Troubleshooting
- Troubleshooting
- Changelog
- GitHub Releases
- Docs Index
- AI Contributor Quickstart (ZH)
- AI Development Rules (ZH)
- Public Roadmap
- Use Cases
- Product Surface Matrix
- Compatibility Matrix
- Testing Guide
- Platform Support
- Architecture
- Project Structure Guide
- Code Entrypoints and Ownership (ZH)
- Product Positioning and Technical Principles (ZH)
- Tool Layering and Risk Classification (ZH)
- Contributing
- Visual Editor
- Release Process
MIT. See LICENSE.