AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
MCP verified MIT Self-run

Hermes Computer Use

mcp-noah3521-hermes-computer-use · by Noah3521

Pixel-level browser automation MCP server — drive a real Chrome with screenshot + xdotool, no CDP, no navigator.webdriver. Pairs with hermes-agent, Claude, Codex, or any MCP client.

No reviews yet
0 installs
7 views
0.0% view→install

Install

$ agentstack add mcp-noah3521-hermes-computer-use

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access Used
  • Filesystem access No
  • Shell / process execution Used
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/mcp-noah3521-hermes-computer-use)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude DesktopCursorWindsurf

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Hermes Computer Use? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

hermes-computer-use

English · [日本語](README.ja.md) · [中文](README.zh.md) · [한국어](README.ko.md)

[](https://github.com/Noah3521/hermes-computer-use/actions/workflows/ci.yml) [](https://pypi.org/project/hermes-computer-use/) [](LICENSE) [](https://www.python.org/) [](docs/WSL_SETUP.md)

> Scope: Windows 11 + WSL2 Ubuntu 22.04 / 24.04 only. See [docs/WSLSETUP.md](docs/WSLSETUP.md).

Pixel-level browser automation MCP server. Gives any MCP-speaking agent (hermes-agent, Claude Code, Codex, …) 21 tools to drive a real Chrome browser in an Xvfb display — screenshots as vision input, OS-level mouse/keyboard as output. No CDP. No navigator.webdriver. No DOM shortcuts.

> What the GIF shows — an agent opens Chrome, focuses the Google search bar, types snp500, presses Enter, and Google returns a full SERP with the live S&P 500 index card. The same flow routinely trips "unusual traffic" or a captcha for Playwright-driven automation. This stack doesn't get flagged because the browser is stock Chrome driven by stock X11 input — there is no automation fingerprint to detect.

Why this exists

| | Playwright / CDP | hermes-computer-use | |---|---|---| | navigator.webdriver | true (detectable) | undefined | | CDP endpoint open | yes | no | | DOM access | direct (fast, brittle to markup changes) | screenshot only (slower, resilient to UI rewrites) | | Anti-bot footprint | large, constantly patched | near-zero: stock Chrome + stock X input | | Best for | flows on sites you own | agents operating unfamiliar sites like a human |

If your automation has to walk a signup funnel on a site guarded by Cloudflare, Kasada, reCAPTCHA, or DataDome, this stack usually passes where Playwright gets stopped.

Evidence: [docs/assets/demo-sannysoft.png](docs/assets/demo-sannysoft.png) — bot.sannysoft.com fingerprint panel with WebDriver, Chrome runtime, Permissions, Plugins, Languages, and PHANTOM all passed.

Architecture

agent ── stdio MCP ──▶ hermes_computer_use.server ── subprocess ──▶ xdotool / scrot
                                                                        │
                                                                        ▼
                                                                    Xvfb :99
                                                                        │
                                                     ┌──────────────────┼──────────────────┐
                                                     ▼                                     ▼
                                               x11vnc :5900                    websockify + noVNC :6080
                                          (native VNC clients)                 (browser viewer)

Longer version: [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md).

Install

Prerequisites: Windows 11, WSL2 with Ubuntu 22.04/24.04, systemd enabled. Full walkthrough: [docs/WSLSETUP.md](docs/WSLSETUP.md).

Everything below runs inside the WSL shell.

From PyPI

pip install "hermes-computer-use[novnc]"

You still need system packages (Xvfb, Chrome, xdotool…) and systemd units — see source install steps 1 & 4.

From source

git clone https://github.com/Noah3521/hermes-computer-use.git ~/hermes-computer-use
cd ~/hermes-computer-use

bash scripts/setup.sh                            # 1. apt + Chrome + uinput (sudo)
python3 -m venv .venv && . .venv/bin/activate
pip install -e ".[novnc]"                        # 2. Python package
bash scripts/install-novnc.sh                    # 3. (optional) web viewer

mkdir -p ~/.config/systemd/user                  # 4. persistent services
cp systemd/*.example ~/.config/systemd/user/
# edit the paths inside to match your clone, then:
sudo loginctl enable-linger "$USER"
systemctl --user daemon-reload
systemctl --user enable --now computer-use.service novnc.service

Smoke test: python examples/smoke_test.py.

Wire to an MCP client

Copy the relevant snippet from [config/hermes.yaml.example](config/hermes.yaml.example) into your agent's MCP server config. Works with hermes-agent, Claude Code, Codex, mcp-inspector, or any stdio MCP client.

Hand the install to an LLM

If your agent has shell + filesystem tools, you can skip the manual install entirely: paste the prompt in [docs/LLM_SETUP_PROMPT.md](docs/LLMSETUPPROMPT.md) and it will clone, install, wire up systemd, run the smoke test, and report back. Available in English, 日本語, 中文, 한국어.

Tools (30)

| Category | Tools | |---|---| | Status | screen_info, cursor_position | | Capture | screenshot | | Pointer | move, left_click, right_click, double_click, middle_click, drag, scroll | | Keyboard | type_text, press_key, hold_key, clear_field, select_all, copy, paste, cut, undo, redo, clipboard_set, clipboard_get | | Timing | wait | | Browser | open_url, new_tab, close_tab, back, forward, reload | | Escape hatch | run_shell | | Optional DOM fast-path (CU_ENABLE_CDP=1) | dom_click, dom_type, dom_query, dom_exists, dom_wait, dom_eval, network_capture, console_messages |

press_key accepts case-insensitive names and aliases — Backspace, backspace, BackSpace all work; cmd+a, command-a, ctrl+a all resolve; meta/win/windows/cmd map to Super.

Opt-in DOM fast-path

For DOM-heavy pages where vision grounding is slow or fragile (SPA dashboards, deep forms), you can opt into CSS-selector-based clicks / typing / queries. Trade-off: Chrome exposes a DevTools port and navigator.webdriver flips to true for the session, which defeats the anti-bot posture on sites that fingerprint Chrome. Off by default.

CU_ENABLE_CDP=1 bash scripts/display.sh restart
pip install "hermes-computer-use[dom]"        # adds websocket-client
# Run the MCP with CU_ENABLE_CDP=1 in its env too (hermes config etc.)

See [docs/ARCHITECTURE.md#dom-fast-path](docs/ARCHITECTURE.md) for when to use which.

Demo prompts

Try any of the prompts in [examples/demo_prompts.md](examples/demo_prompts.md). The simplest and most illustrative:

> "Use computer_use to open Google, search for snp500, and tell me the current S&P 500 index price from the page."

Open http://localhost:6080/vnc.html in a browser while the agent runs — watching the cursor arc through the search bar is surprisingly compelling.

Configuration (env vars)

| Var | Default | Meaning | |---|---|---| | CU_DISPLAY | 99 | X display number | | CU_WIDTH / CU_HEIGHT | 1440 / 900 | Virtual screen size | | CU_VNC_PORT | 5900 | x11vnc listen port | | CU_STATE_DIR | /tmp/hermes-computer-use | Logs, PID files | | CU_PROFILE_DIR | $CU_STATE_DIR/chrome-profile | Persistent Chrome profile | | CU_START_URL | about:blank | First URL Chrome opens | | CU_INPUT | xdotool | Set to ydotool for /dev/uinput input | | CU_KEY_DELAY_MS | 25 | Inter-keystroke delay | | CU_MOVE_STEPS | 18 | Cursor interpolation steps |

Docs

  • [WSLSETUP.md](docs/WSLSETUP.md) — Windows-side setup, systemd, linger
  • [ARCHITECTURE.md](docs/ARCHITECTURE.md) — internals + design rationale
  • [CAPTCHA.md](docs/CAPTCHA.md) — what passive / behavioural / visual challenges this approach can and cannot handle
  • [TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md) — common failure modes with fixes
  • [FAQ.md](docs/FAQ.md) — Playwright comparison, anti-bot honesty, parallel runs, profile safety
  • [SECURITY.md](SECURITY.md) — threat model and hardening checklist

Security

This is an LLM with hands. Read [SECURITY.md](SECURITY.md). Baseline:

  • Run in an isolated WSL distro, not your daily driver.
  • Strip run_shell if the agent doesn't need shell access.
  • Don't persist real credentials in CU_PROFILE_DIR.

Contributing

See [CONTRIBUTING.md](CONTRIBUTING.md). The guiding thesis is "emit no abnormal signals by default" > "emit clever evasions" — but additive hybrid paths (e.g. opt-in DOM / CDP fast-clicks that users turn on per-site) are welcome when they do not flip the default posture.

License

MIT. See [LICENSE](LICENSE).

Acknowledgements

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.