mcp-helm
Enables automation of Apple services (like App Store Connect) by driving a real Chrome browser with handoff awareness for sensitive actions.
Allows automating Cloudflare dashboard tasks, including navigating and interacting with the Cloudflare web interface via Chrome.
Supports automation of Google Play Console and other Google services through browser interaction tools such as navigation, clicking, and typing.
Allows automating the Stripe dashboard, including navigation, clicking, and form filling, through a live Chrome session attached to the user's browser.
Enables automation of Vercel dashboard operations by driving a real Chrome browser with screenshot diff and handoff detection.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-helm log into Stripe and check the latest payments"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-helm
Drive your real Chrome session from Claude — copilot mode, with handoff awareness.
Most browser-automation MCP servers spawn a fresh Playwright Chromium. That's useless when the work is "log into Stripe and click 5 things" — you don't have your cookies, your 2FA, your bookmarks. mcp-helm attaches to YOUR Chrome, the one you're already signed into, and lets Claude run a small set of tools against the active tab.
It also knows when to step back: when the page shows a 2FA prompt, captcha,
payment confirmation, or biometric request, the screenshot tool flags it and
Claude can call handoff() to wait for you.
Why this exists
The eyes-and-hands problem: Claude tells you "click Settings → API access" and you click Settings and there is no API access, so you screenshot back to Claude, which guesses again. That's 5 minutes of round-trips for a 5-second task, and it happens on every Stripe / Apple / Play Console / Cloudflare / Vercel setup.
mcp-helm cuts that loop. Claude sees the actual page, picks elements from the accessibility tree (no coordinate guessing), and stops when it would do something it shouldn't.
Related MCP server: chrome-bridge
Install
npm install -g mcp-helmAdd to ~/.claude.json (or your MCP client's config):
{
"mcpServers": {
"helm": {
"command": "mcp-helm"
}
}
}Usage
1. Launch a driveable Chrome
Add this alias to your shell rc:
alias chrome-pilot='open -a "Google Chrome" --args --remote-debugging-port=9222 --user-data-dir=$HOME/.chrome-pilot'Run it once: chrome-pilot. A separate Chrome profile opens. Sign into
everything you'd want Claude to drive (Play Console, Stripe, etc.).
Cookies persist across launches — you only sign in once per service.
Why a separate profile? Your main Chrome can't be launched in remote-debugging mode while it's already running. The dedicated profile lives in
~/.chrome-pilotand stays separate from your daily browsing.
2. From Claude
You: Upload the AAB at <path> to Play Store internal testing.
Claude: [calls helm.attach] → [helm.navigate to play.google.com/console]
[helm.screenshot] → sees the dashboard
[helm.click "Personalized AI Portfolio Bot"]
... etcIf a 2FA prompt appears, screenshot returns
handoffTriggers: ["2FA prompt"] and Claude calls handoff to wait.
Tools
Tool | Purpose |
| Connect to Chrome on port 9222. Always call first. |
| List all open tabs. |
| Switch active tab by index or URL substring. |
| PNG + URL + title + handoff triggers detected. |
| Numbered list of interactive elements (a11y tree). |
| Click by id (from inspect), text, or CSS selector. Returns |
| Type into a field. |
| Go to a URL. |
| Wait for text or selector. |
| Pause and ask the human to take over. |
Design choices
Accessibility tree, not coordinates. Vision-grounded clicking (Anthropic computer use) is great but flaky on Retina displays and high-DPR scaling. The a11y tree gives stable, semantic IDs — and is what screen readers use.
Screenshot diff after every click. If
changed: false, the click was a no-op. Saves Claude from cheerfully reporting success.Handoff detection is regex-based, not LLM-based. Cheap, fast, no false positives on common login phrases.
No tab-management heuristics.
attachpicks the first non-blank tab; uselist_tabs+focus_tabto be precise. Predictable beats clever.
Status
v0.1 — works for simple flows (Play Console, Stripe dashboard, Vercel, Cloudflare). Edge cases this doesn't handle yet:
Shadow DOM components (some web-component-heavy sites)
iframes (need to surface frame switching)
File uploads from disk
Keyboard shortcuts beyond Enter
License
MIT
Available Tools
10 toolsattachA
Connect to a running Chrome instance (must be launched with --remote-debugging-port). Returns the active tab URL and total tab count. Always call this first.
Inputs: port.
clickA
Click by id (from inspect), by visible text, or by CSS selector. Returns {changed: true/false} based on a pre/post screenshot diff — false means the click had no effect.
Inputs: id, text, selector.
focus_tabB
Switch the active tab by index (from list_tabs) or by URL substring.
Inputs: index, urlContains.
handoffA
Pause and ask the human to complete the next step manually (2FA, payment, sensitive config). Returns a paused state — the human resolves it in the browser, then tells Claude to continue.
Inputs: reason (required).
inspectA
Return a numbered list of interactive elements (buttons, links, inputs) from the accessibility tree. Use the returned id with click() or type() — no coordinates needed.
Inputs: no named parameters.
list_tabsA
List all open tabs across contexts. Use to find a specific tab to focus.
Inputs: no named parameters.
screenshotA
Capture the active tab. Returns base64 PNG, URL, title, and any detected handoff triggers (2FA, captcha, payment prompts). Call this after every action to verify state.
Inputs: fullPage.
typeC
Type into a field by id (from inspect) or CSS selector. Set submit=true to press Enter after.
Inputs: text (required), id, selector, submit.
wait_forC
Wait for visible text or a CSS selector to appear on the page.
Inputs: text, selector, timeoutMs.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Each tool has a clearly distinct purpose: attaching, navigating, clicking, typing, inspecting, tab management, screenshotting, waiting, and handoff. No overlapping functionality.
All tool names follow a consistent verb or verb_noun pattern with lowercase and underscores (e.g., focus_tab, list_tabs, wait_for). No mixing of conventions.
With 10 tools, the set covers core browser automation tasks without being bloated or sparse. Each tool earns its place.
The tool surface covers connection, navigation, interaction, inspection, tab management, and human handoff. Minor gap: no explicit scrolling or back/forward navigation, but these are often handled indirectly.
Maintenance
Related MCP Connectors
Let AI agents use your real, signed-in Chrome: tabs, clicks, forms, screenshots and video.
Give AI agents a real cloud Chrome: open sessions, navigate, read pages, click, type and screenshot.
Let AI agents use any website you're logged in to. Sessions stay encrypted on your machine.
Let AI agents observe and control Chrome tabs you explicitly share via Browse Bridge.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceTransforms Chrome browser into an AI-controlled automation tool that allows AI assistants like Claude to access browser functionality, enabling complex automation, content analysis, and semantic search while preserving your existing browser environment.MIT
- FlicenseNot gradedqualityCmaintenanceProvides a direct bridge between Claude and an authenticated Chrome session, enabling fetch requests with session cookies and JavaScript execution within live web pages.-
- AlicenseNot gradedqualityDmaintenanceChrome extension + MCP bridge that gives Claude control over your real browser via CDP, enabling navigation, clicking, typing, scrolling, screenshots, and JS execution with a visible cursor and tab-bring-to-front.1MIT
- AlicenseNot gradedqualityBmaintenanceLets Claude Code drive your own Chrome browser with human-like clicks, drags, and typing. It uses your real sessions and logins, and pauses for your confirmation on anything irreversible.8MIT