local-chrome-cdp-probe-mcp
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., "@local-chrome-cdp-probe-mcpmeasure the checkout button and screenshot it, hiding the login modal"
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.
local-chrome-cdp-probe-mcp
Real-browser measurement + screenshots through your local Chrome via the Chrome DevTools Protocol. Zero npm dependencies (Node >= 20 global fetch/WebSocket), zero Python deps beyond the MCP SDK. For when Playwright is not cached and agent-browser is not installed, but the bug report is "this button looks squashed on my screen".
Why this exists — the traps it removes
Trap | Symptom | Handled by |
| plain text "Using unsafe HTTP verb GET..." then | probe uses PUT (Chrome >= 111 contract) |
Host sandbox kills Chrome's sandbox | renderer dies, DevTools ws closes with 1006 immediately |
|
Node WebSocket sends an Origin header | DevTools rejects the upgrade, 1006 |
|
Retina display doubles physical pixels | measured sizes 2x of CSS px |
|
httpOnly login cookies unreachable from scripts | "just set document.cookie" fails | login is a |
Modal overlays ruin screenshots | shot full of forced-password-change mask | your measure_js can remove the mask before capture |
Related MCP server: chrome-mcp
Install & run
pip install -e . # mcp only
node --version # must be >= 20
python server.py # stdio transport{
"mcpServers": {
"local-chrome-cdp-probe": {
"command": "python",
"args": ["/path/to/local-chrome-cdp-probe-mcp/server.py"]
}
}
}Optional env: CHROME_PATH (any Chromium), NODE_BIN (default node),
PROBE_TIMEOUT (wrapper timeout, default 60s; per-probe --timeout-ms
default 30s).
Smoke test
python test_smoke.py # real Chrome round trip on a local file:// pageLicense: MIT.
This server cannot be deployed
Maintenance
Related MCP Connectors
Hosted real Google Chrome MCP with per-user persistent state. Navigate, click, type, screenshot.
Browser MCP for logged-in tasks. Uses your Chrome — credentials stay local. Zero-token replay.
Browserless MCP — wraps the Browserless headless-Chromium REST API (browserless.io)
Automate cloud Chrome—navigate, click, type, screenshot, run code, record screen video
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables MCP clients to drive a real, logged-in Chrome browser for web automation tasks like navigation, clicking, typing, and screenshotting.2 npmMIT
- FlicenseNot gradedqualityDmaintenanceDrive your real, signed-in Chrome browser from any MCP client, enabling browser automation such as navigation, clicking, typing, and screenshots through standard MCP tools.1-
- AlicenseNot gradedqualityCmaintenanceEnables fast browser automation on a real Chrome tab via a local hub, providing MCP tools for clicking, filling, snapshotting, and navigating without launching a full browser instance.MIT
- AlicenseNot gradedqualityAmaintenanceEnables driving a real Chrome instance remotely through MCP, including per-tab control, JavaScript evaluation, screenshots, cookie and network capture, and CDP fallback with token-based authentication.2MIT