chrome-devtools-mcp-skill
Use Chrome DevTools MCP through UXC over local stdio for page navigation, DOM/a11y snapshots, network inspection, console inspection, and performance tooling, with a live-browser autoConnect default and optional browserUrl or isolated fallback modes.
How do I install this agent skill?
npx skills add https://github.com/holon-run/uxc --skill chrome-devtools-mcp-skillIs this agent skill safe to install?
- Gen Agent Trust Hubpass
This skill enables an agent to control and inspect a Google Chrome browser using the Chrome DevTools MCP server. It utilizes standard development tools like npx to fetch the required package and interacts with the browser's local remote debugging port. The skill's operations are consistent with its stated purpose of browser automation and performance analysis.
- Socketpass
No alerts
- Snykwarn
Risk: MEDIUM · 1 issue
What does this agent skill do?
Chrome DevTools MCP Skill
Use this skill to run Chrome DevTools MCP operations through uxc using a fixed stdio endpoint.
Reuse the uxc skill for generic MCP discovery, daemon reuse, JSON envelope parsing, and error handling.
Prerequisites
uxcis installed and available inPATH.npxis available inPATH(Node.js installed).- Chrome 144+ is running locally with remote debugging enabled from
chrome://inspect/#remote-debuggingif you use the default live-browser flow. - Network access is available for first-time
chrome-devtools-mcppackage fetch.
Core Workflow (Chrome DevTools MCP-Specific)
Endpoint candidate inputs before finalizing:
- Raw package form from official docs:
npx chrome-devtools-mcp@latest
- Reliable non-interactive form:
npx -y chrome-devtools-mcp@latest
- Default live-browser endpoint for this skill:
npx -y chrome-devtools-mcp@latest --autoConnect --no-usage-statistics
- Explicit browser-url endpoint:
npx -y chrome-devtools-mcp@latest --browserUrl http://127.0.0.1:9222 --no-usage-statistics
- Fallback isolated endpoint:
npx -y chrome-devtools-mcp@latest --headless --isolated --no-usage-statistics
- Running local Chrome auto-connect mode:
npx -y chrome-devtools-mcp@latest --autoConnect --no-usage-statistics
- Verify protocol/path from official source and probe:
- Official source:
https://github.com/ChromeDevTools/chrome-devtools-mcp
- probe candidate endpoints with:
uxc "npx -y chrome-devtools-mcp@latest --autoConnect --no-usage-statistics" -h
- Confirm protocol is MCP stdio (
protocol == "mcp"in envelope).
- Official source:
- Detect auth requirement explicitly:
- Run host help or a minimal read call and inspect envelope.
- Default local stdio flow requires no OAuth/API key.
- Existing Chrome attachment requires remote debugging to be enabled separately, but not API auth.
- Use a fixed link command by default:
command -v chrome-devtools-mcp-cli- If missing, create it:
uxc link chrome-devtools-mcp-cli "npx -y chrome-devtools-mcp@latest --autoConnect --no-usage-statistics"
- Optional explicit browser-url link:
command -v chrome-devtools-mcp-portuxc link chrome-devtools-mcp-port "npx -y chrome-devtools-mcp@latest --browserUrl http://127.0.0.1:9222 --no-usage-statistics"
- Optional isolated fallback link:
command -v chrome-devtools-mcp-isolateduxc link chrome-devtools-mcp-isolated "npx -y chrome-devtools-mcp@latest --headless --isolated --no-usage-statistics"
chrome-devtools-mcp-cli -h
- Inspect operation schema before execution:
chrome-devtools-mcp-cli new_page -hchrome-devtools-mcp-cli take_snapshot -hchrome-devtools-mcp-cli list_network_requests -hchrome-devtools-mcp-cli lighthouse_audit -h
- Prefer read-first interaction:
- Start with
new_page,list_pages,take_snapshot,list_network_requests, orlist_console_messages.
- Start with
- Confirm before mutating page state:
clickfillfill_formpress_keyupload_fileevaluate_scripthandle_dialog
Guardrails
- Keep automation on the JSON output envelope; do not rely on
--text. - Use
chrome-devtools-mcp-clias the default command path. - Prefer the live-browser default endpoint when you need real logged-in state, current tabs, network diagnostics, console inspection, or performance analysis.
- Prefer
--autoConnectfirst when browser-side remote debugging is available. - Use
chrome-devtools-mcp-portonly when you intentionally run a Chrome instance with--remote-debugging-port=9222. - If no debuggable Chrome is available, fallback to
chrome-devtools-mcp-isolated. - Prefer
take_snapshotover screenshots for model-action loops. - Prefer
list_network_requests/get_network_requestover raw script evaluation when inspecting network behavior. - Treat
lighthouse_audit,performance_start_trace, andtake_memory_snapshotas heavier operations; use them intentionally. - Use
evaluate_scriptonly when an existing higher-level DevTools tool cannot answer the question.
References
- Invocation patterns:
references/usage-patterns.md
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/holon-run/uxc/chrome-devtools-mcp-skill">View chrome-devtools-mcp-skill on skillZs</a>