OpenChrome

Smart. Fast. Parallel.
Browser automation MCP server that uses your real Chrome.

What is OpenChrome?

Imagine 20+ parallel Playwright sessions — but already logged in to everything, invisible to bot detection, and sharing one Chrome process at 300MB. That's OpenChrome.

Search across 20 sites simultaneously. Crawl authenticated dashboards in seconds. Debug production UIs with real user sessions. Connect to OpenClaw and give your AI agent browser superpowers across Telegram, Discord, or any chat platform.

You: oc compare "AirPods Pro" prices across Amazon, eBay, Walmart,
     Best Buy, Target, Costco, B&H, Newegg — find the lowest

AI:  [8 parallel workers, all sites simultaneously]
     Best Buy:  $179 ← lowest (sale)
     Amazon:    $189
     Costco:    $194 (members)
     ...
     Time: 2.8s | All prices from live pages, already logged in.

Guided, Not Guessing

The bottleneck in browser automation isn't the browser — it's the LLM thinking between each step. Every tool call costs 5–15 seconds of inference time. When an AI agent guesses wrong, it doesn't just fail — it spends another 10 seconds thinking about why, then another 10 seconds trying something else.

Playwright agent checking prices on 5 sites:

  Site 1:  launch browser           3s
           navigate                  2s
           ⚡ bot detection          LLM thinks... 12s → retry with UA
           ⚡ CAPTCHA                LLM thinks... 10s → stuck, skip
           navigate to login         2s
           ⚡ no session             LLM thinks... 12s → fill credentials
           2FA prompt               LLM thinks... 10s → stuck
           ...
           finally reaches product   after ~20 LLM calls, ~4 minutes

  × 5 sites, sequential  =  ~100 LLM calls,  ~20 minutes,  ~$2.00

  Actual work: 5 calls.  Wasted on wandering: 95 calls.

OpenChrome eliminates this entirely — your Chrome is already logged in, and the hint engine corrects mistakes before they cascade:

OpenChrome agent checking prices on 5 sites:

  All 5 sites in parallel:
    navigate (already authenticated)     1s
    read prices                          2s
    ⚡ stale ref on one site
      └─ Hint: "Use read_page for fresh refs"    ← no guessing
    read_page → done                     1s

  = ~20 LLM calls,  ~15 seconds,  ~$0.40

The hint engine watches every tool call across 6 layers — error recovery, composite suggestions, repetition detection, sequence detection, learned patterns, and success guidance. When it sees the same error→recovery pattern 3+ times, it promotes it to a permanent rule across sessions.

Quick Start

npx openchrome-mcp setup

That's it. Say oc to your AI agent.

claude mcp add openchrome -- npx -y openchrome-mcp serve --auto-launch

{
  "servers": {
    "openchrome": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "openchrome-mcp", "serve", "--auto-launch"]
    }
  }
}

{
  "mcpServers": {
    "openchrome": {
      "command": "npx",
      "args": ["-y", "openchrome-mcp", "serve", "--auto-launch"]
    }
  }
}

Examples

Parallel monitoring:

oc screenshot AWS billing, GCP console, Stripe, and Datadog — all at once
→ 4 workers, 3.1s, already authenticated everywhere

Multi-account:

oc check orders on personal and business Amazon accounts simultaneously
→ 2 workers, isolated sessions, same site different accounts

Competitive intelligence:

oc compare prices for "AirPods Pro" across Amazon, eBay, Walmart, Best Buy
→ 4 workers, 4 sites, 2.4s, works past bot detection

47 Tools

CLI

oc setup                    # Auto-configure
oc serve --auto-launch      # Start server
oc serve --headless-shell   # Headless mode
oc doctor                   # Diagnose issues

Cross-Platform

DOM Mode (Token Efficient)

read_page supports three output modes:

DOM mode example:

read_page tabId="tab1" mode="dom"

[page_stats] url: https://example.com | title: Example | scroll: 0,0 | viewport: 1920x1080

[142]<input type="search" placeholder="Search..." aria-label="Search"/>
[156]<button type="submit"/>Search
[289]<a href="/home"/>Home
[352]<h1/>Welcome to Example

DOM mode outputs [backendNodeId] as stable identifiers — they persist for the lifetime of the DOM node, unlike ref_N IDs which are cleared on each AX-mode read_page call.

Stable Selectors

Action tools that accept a ref parameter (form_input, computer, etc.) support three identifier formats:

Backward compatible — existing ref_N workflows work unchanged. DOM mode's backendNodeId eliminates "ref not found" errors caused by stale references.

Session Persistence

Headless mode (--headless-shell) doesn't persist cookies across restarts. Enable storage state persistence to maintain authenticated sessions:

oc serve --persist-storage                         # Enable persistence
oc serve --persist-storage --storage-dir ./state    # Custom directory

Cookies and localStorage are saved atomically every 30 seconds and restored on session creation.

Benchmarks

Measure token efficiency and parallel performance:

npm run benchmark                                    # Stub mode: AX vs DOM token efficiency (interactive)
npm run benchmark:ci                                 # Stub mode: AX vs DOM with JSON + regression detection
npm run benchmark -- --mode real                     # Real mode: actual MCP server (requires Chrome)
npx ts-node tests/benchmark/run-parallel.ts          # Stub mode: all parallel benchmark categories
npx ts-node tests/benchmark/run-parallel.ts --mode real --category batch-js --runs 1  # Real mode
npx ts-node tests/benchmark/run-parallel.ts --mode real --category realworld --runs 1  # Real-world benchmarks

By default, benchmarks run in stub mode — measuring protocol correctness and tool-call counts with mock responses. Use --mode real to spawn an actual MCP server subprocess and measure real performance (requires Chrome to be available).

Parallel benchmark categories:

Development

git clone https://github.com/shaun0927/openchrome.git
cd openchrome
npm install && npm run build && npm test

License

MIT