Docker Stealthy Auto Browse MCP Server

docker-stealthy-auto-browse

Stealth browser automation that actually works. Runs Camoufox (custom Firefox) in Docker with zero Chrome DevTools Protocol exposure, real OS-level mouse and keyboard input via PyAutoGUI, and a JSON HTTP API + MCP server to control it all remotely. Watch it live via noVNC. Run a single instance or spin up a cluster behind HAProxy with Redis cookie sync, request queuing, and sticky sessions. Drive it with curl, pipe YAML scripts through stdin, send multi-step scripts via the API, use page loaders to auto-handle popups and paywalls, or connect AI agents directly via MCP. Optional Bearer token auth via AUTH_TOKEN.

Passes Cloudflare, CreepJS, BrowserScan, Pixelscan, and every other bot detector we've thrown at it. While Chromium-based tools are getting caught by the first line of defense, this thing walks through the front door unnoticed.

Table of Contents

• What's Inside
• Quick Start
• Two Input Modes
• Virtual Camera & Microphone
• MCP Server
• Agent integrations
• Script Mode
• Page Loaders
• Screen Recording
• Cluster Mode
• Authentication
• Configuration
• Development
• Bot Detection Results
• License

What's Inside

Pre-installed extensions: uBlock Origin (ads/trackers), LocalCDN (prevents CDN tracking), ClearURLs (strips tracking params), Consent-O-Matic (auto-handles cookie popups).

Quick Start

docker run -d --name browser \
  -p 8080:8080 \
  -p 5900:5900 \
  psyb0t/stealthy-auto-browse

Port 8080 is the HTTP API, port 5900 is the VNC viewer (http://localhost:5900/).

# Navigate
curl -X POST http://localhost:8080 \
  -H "Content-Type: application/json" \
  -d '{"action": "goto", "url": "https://example.com"}'

# Get page text
curl -X POST http://localhost:8080 \
  -H "Content-Type: application/json" \
  -d '{"action": "get_text"}'

# Click by CSS selector (preferred — fast and reliable)
curl -X POST http://localhost:8080 \
  -H "Content-Type: application/json" \
  -d '{"action": "click", "selector": "button#submit"}'

# Screenshot (last resort — prefer get_text; always resize to save tokens)
curl "http://localhost:8080/screenshot/browser?whLargest=512" -o screenshot.png

Run multi-step scripts in one request:

curl -X POST http://localhost:8080 \
  -H "Content-Type: application/json" \
  -d '{
    "action": "run_script",
    "steps": [
      {"action": "goto", "url": "https://example.com", "wait_until": "domcontentloaded"},
      {"action": "sleep", "duration": 2},
      {"action": "get_text", "output_id": "text"},
      {"action": "eval", "expression": "document.title", "output_id": "title"}
    ]
  }'

Also accepts "yaml": "..." with the same YAML format used in script mode. In single-instance mode, requests are serialized automatically — send multiple scripts in parallel and they queue up.

See docs/api.md for all actions and the full API reference.

Navigation uses app-owned controls, not a hidden browser-library timeout: each attempt gets 30 seconds by default, one timeout retry, and a one-second retry delay. Pass timeout, retry_count, and retry_delay with goto, refresh, or new_tab when a workflow needs different bounds. retry_count: 0 disables retries. See navigation controls for the limits and retry behavior.

Two Input Modes

There are two ways to interact with pages. System input uses PyAutoGUI to generate real OS-level mouse and keyboard events — the browser cannot tell these apart from a real human. Playwright input uses CSS selectors and DOM event injection — easier, but theoretically detectable by behavioral analysis. Use system input on any site with bot protection.

Full breakdown and usage guide: docs/stealth.md

Virtual Camera & Microphone

Mount test media read-only at /media and set VIRTUAL_CAMERA_FILE and/or VIRTUAL_MICROPHONE_FILE. Pages that call navigator.mediaDevices.getUserMedia() receive tracks captured from those files, so camera and microphone checks can run without host hardware.

docker run -d -p 8080:8080 \
  -v ./media:/media:ro \
  -e VIRTUAL_CAMERA_FILE=camera.webm \
  -e VIRTUAL_MICROPHONE_FILE=microphone.wav \
  psyb0t/stealthy-auto-browse

Sources must remain inside /media; restart the browser after changing them. A request for a kind without a configured virtual source fails with NotFoundError rather than falling back to hardware. Virtual tracks use the source file's native format, so pages must not require incompatible exact media constraints. This virtualizes getUserMedia() only, not enumerateDevices().

To switch sources during an authorized test without replacing an already acquired camera or microphone track, enable VIRTUAL_MEDIA_DYNAMIC=true. Dynamic mode is disabled by default. Use set_virtual_media_source to choose an existing relative file name under VIRTUAL_MEDIA_DIR, or upload_virtual_media to add bounded base64 content and optionally activate it. An upload filename is only a safe, type-matching media name; the service generates a collision-safe stored basename, returns it, and never overwrites an existing named source. Before storage or activation, the decoded upload is checked with ffprobe for a stream matching the requested camera or microphone kind. The media directory must be writable for uploads; VIRTUAL_MEDIA_UPLOAD_MAX_BYTES defaults to 50 MiB. Existing page streams keep their track identities while the source changes.

Dynamic mode accepts files from the configured media directory only. It does not accept arbitrary host paths, remote URLs, WebSocket streams, or other live ingress. Both actions use the normal API authentication: when AUTH_TOKEN is set, send the usual Authorization: Bearer <token> header. See docs/api.md#virtual-camera-and-microphone and docs/configuration.md for the action contract and writable-volume setup.

MCP Server

AI agents can control the browser over the Model Context Protocol via Streamable HTTP at /mcp on the same port 8080. All browser actions are exposed as MCP tools — navigation, screenshots, clicking, typing, JavaScript evaluation, cookies, and more.

For authorised test flows that need a human review when a verification widget appears, use detect_challenge. It is read-only: it reports a best-effort absent, present, or unknown status with bounded vendor/location evidence, but never clicks, enters a frame, or solves a challenge. Pass scroll_into_view: true to bring the first visible detected frame or widget into the viewport for VNC handoff; it still never clicks or focuses it. In cluster mode, include it as a run_script step. See the API reference.

Connect any MCP-compatible client (Claude Desktop, Claude Code, custom agents) to http://localhost:8080/mcp/ and start browsing.

Works in both standalone and cluster mode.

Agent integrations

The skill works in any agent that reads .agents/skills/, and installs natively in the clients below.

Claude Code

claude plugin marketplace add psyb0t/agents
claude plugin install stealthy-auto-browse@psyb0t

Claude Code prompts for the stealthy-auto-browse URL and, if auth is enabled, the token — the token is stored in your OS keychain.

Codex

codex plugin marketplace add psyb0t/agents
codex plugin add stealthy-auto-browse@psyb0t

Installed via the marketplace, the skill invokes as $stealthy-auto-browse:stealthy-auto-browse. Codex also picks the skill up automatically with no install in any repo containing .agents/skills/, where it invokes as plain $stealthy-auto-browse.

OpenClaw

The skill is published to ClawHub on every release:

openclaw skills install @psyb0t/stealthy-auto-browse

For MCP clients that speak local stdio, the @psyb0t/stealthy-auto-browse plugin bridges to the service's /mcp endpoint:

openclaw plugins install clawhub:@psyb0t/stealthy-auto-browse

Then set STEALTHY_AUTO_BROWSE_URL (and AUTH_TOKEN if the server requires auth).

Script Mode

Pipe a YAML script into the container, get JSON results on stdout, container exits. No HTTP server. Good for CI, cron jobs, one-shot scraping.

cat my-script.yaml | docker run --rm -i \
  -e TARGET_URL=https://example.com \
  psyb0t/stealthy-auto-browse --script > results.json

Full docs: docs/script-mode.md

Script mode also supports explicit if branches plus bounded repeat and while loops. Conditions can inspect elements, visible text, URLs, JavaScript booleans, and prior output_id values; see the control-flow reference.

Page Loaders

Define URL patterns + action sequences in YAML files. Mount them at /loaders. Whenever goto matches a pattern, the loader runs automatically — removes popups, waits for content, cleans up the page. Greasemonkey for the HTTP API.

Full docs: docs/page-loaders.md

Screen Recording

Record the browser as MP4 with mouse cursor visible. ffmpeg x11grab against Xvfb writes to a mounted /recordings volume. Three modes: window (full Camoufox window), viewport (chrome cropped using calibrated mozInnerScreenX/Y), desktop (entire Xvfb screen). Slug provided at stop time so you name the file after the run completes. Path-traversal-safe, collision-safe, crash-safe.

mkdir -p ./recordings
docker run -d -p 8080:8080 -v ./recordings:/recordings psyb0t/stealthy-auto-browse

curl -X POST http://localhost:8080 \
  -H "Content-Type: application/json" \
  -d '{"action": "start_recording", "mode": "viewport", "fps": 20}'

# … do stuff …

curl -X POST http://localhost:8080 \
  -H "Content-Type: application/json" \
  -d '{"action": "stop_recording", "slug": "my-flow"}'
# → ./recordings/my-flow.mp4

Also works inside run_script (cluster-mode safe: start and stop must live in the same run_script so both hit the same instance). Full action table + script-mode example + notes in docs/api.md#screen-recording.

Cluster Mode

Run multiple browser instances behind HAProxy with a request queue, sticky sessions, and Redis cookie sync (default 5, configurable via NUM_REPLICAS). Download the compose file and HAProxy config, then start:

curl -LO https://raw.githubusercontent.com/psyb0t/docker-stealthy-auto-browse/main/docker-compose.cluster.yml
docker compose -f docker-compose.cluster.yml up -d

Cookies set on any instance propagate to all others instantly via Redis PubSub. Log in once, the whole fleet is authenticated.

Each browser defaults to a 5GB memory limit. Set BROWSER_MEMORY_LIMIT and BROWSER_MEMORY_RESERVATION when your fleet or display resolution needs a different budget; see cluster mode.

Script-only enforcement (v1.0.0+): When NUM_REPLICAS > 1, both the HTTP API and MCP server restrict to run_script only (plus ping and sleep). Individual actions are rejected to prevent stale content bugs from cross-instance routing. All actions remain available as steps inside run_script.

Full docs: docs/cluster-mode.md

Authentication

Set AUTH_TOKEN to require a Bearer token on all requests (except /health):

docker run -d -p 8080:8080 -e AUTH_TOKEN=your-token-here psyb0t/stealthy-auto-browse

Pass the token in the Authorization header:

# Header
curl -H "Authorization: Bearer your-token-here" http://localhost:8080 ...

Examples

See .agents/skills/stealthy-auto-browse/scripts/ for ready-to-use scripts:

• websearch.py — Multi-engine parallel web search (Brave, Google, Bing) with structured results and AI overview extraction. Outputs JSON with title, URL, and snippet for each result.

Configuration

Full environment variables table, proxy setup (including a working private pr0xteus HTTP-proxy example), persistent profiles, browser extensions, and VNC access: docs/configuration.md

Development

Docker is the only development dependency. The Makefile builds a local browser base, then runs linting, tests, and security tools in a separate disposable dev container. Only the complete test target receives the Docker socket because it starts its own browser and fixture containers.

make build
make lint
make test
make sec

make sec writes sec.sarif for GitHub Security. It reports findings without blocking a release. Use make help for the complete command list.

Bot Detection Results

Why it works: docs/stealth.md

Known Issues / TODO

• system_click reliability — OS-level mouse clicks can land in the wrong place if the window offset is stale. Needs a more robust coordinate mapping solution so it works reliably without manual calibrate calls.

License

WTFPL — Do What The Fuck You Want To Public License