Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/insilications/chrome-devtools-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/insilications/chrome-devtools-mcp/gemini-extension)<a href="https://agentmods.dev/plugins/insilications/chrome-devtools-mcp/gemini-extension"><img src="https://agentmods.dev/badge/plugins/insilications/chrome-devtools-mcp/gemini-extension/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/insilications/chrome-devtools-mcp/gemini-extension"><img src="https://agentmods.dev/badge/plugins/insilications/chrome-devtools-mcp/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
chrome-devtools-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to chrome-devtools-mcp — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"name": "chrome-devtools-mcp",
"version": "1.8.0",
"mcpServers": {
"chrome-devtools": {
"command": "npx",
"args": [
"[email protected]"
]
}
}
}
What ships with it
47 files beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/append-lighthouse-notices.ts 799 B runs code
- scripts/count_tokens.ts 906 B runs code
- scripts/eslint_rules/check-license-rule.js 2.4 KB runs code
- scripts/eslint_rules/enforce-zod-schema-rule.js 1.6 KB runs code
- scripts/eslint_rules/local-plugin.js 487 B runs code
- scripts/eslint_rules/no-direct-third-party-imports-rule.js 4.1 KB runs code
- scripts/eval_gemini.ts 7.4 KB runs code
- scripts/eval_result.ts 2.8 KB runs code
- scripts/eval_scenarios/console_test.ts 759 B runs code
- scripts/eval_scenarios/emulation_test.ts 547 B runs code
- scripts/eval_scenarios/emulation_userAgent_test.ts 798 B runs code
- scripts/eval_scenarios/emulation_viewport_test.ts 674 B runs code
- scripts/eval_scenarios/fill_select_and_checkboxes_test.ts 3.0 KB runs code
- scripts/eval_scenarios/fix_webpage_issues_test.ts 1.9 KB runs code
- scripts/eval_scenarios/frontend_snapshot_test.ts 853 B runs code
- scripts/eval_scenarios/input_parallel_test.ts 1.0 KB runs code
- scripts/eval_scenarios/input_test.ts 944 B runs code
- scripts/eval_scenarios/isolated_context_test.ts 633 B runs code
- scripts/eval_scenarios/lighthouse_a11y_test.ts 884 B runs code
- scripts/eval_scenarios/lighthouse_best_practices_test.ts 891 B runs code
- scripts/eval_scenarios/navigation_test.ts 656 B runs code
- scripts/eval_scenarios/network_test.ts 775 B runs code
- scripts/eval_scenarios/page_focus_keyboard_test.ts 2.4 KB runs code
- scripts/eval_scenarios/page_id_routing_concurrent_form_test.ts 2.7 KB runs code
- scripts/eval_scenarios/page_id_routing_cross_page_state_test.ts 3.1 KB runs code
- scripts/eval_scenarios/page_id_routing_test.ts 1.8 KB runs code
- scripts/eval_scenarios/performance_test.ts 559 B runs code
- scripts/eval_scenarios/select_page_test.ts 695 B runs code
- scripts/eval_scenarios/snapshot_test.ts 639 B runs code
- scripts/generate-cli.ts 6.2 KB runs code
- scripts/generate-docs.ts 17 KB runs code
- scripts/post-build.ts 5.9 KB runs code
- scripts/prepare.ts 2.4 KB runs code
- scripts/profile/inspector.ts 4.2 KB runs code
- scripts/profile/profile_mcp.ts 11 KB runs code
- scripts/profile/scenarios/get_console_messages.ts 710 B runs code
- scripts/profile/scenarios/navigation.ts 893 B runs code
- scripts/profile/scenarios/page_churn.ts 1.0 KB runs code
- scripts/profile/source_map_server.ts 3.5 KB runs code
- scripts/profile/types.ts 777 B runs code
- scripts/profile/utils.ts 1.8 KB runs code
- scripts/test.js 2.9 KB runs code
- scripts/tsconfig.json 622 B
- scripts/update_metrics.ts 3.9 KB runs code
- scripts/update-lighthouse.ts 1.4 KB runs code
- scripts/verify-npm-package.js 1.2 KB runs code
- scripts/verify-server-json-version.ts 2.3 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 13 lines scan A 2120ea03f5bf
chrome-devtools-mcp is a plugin published in the GitHub repository insilications/chrome-devtools-mcp (0 stars, last pushed 2d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. It is 100% identical to chrome-devtools-mcp, differing in 4 lines, and is treated as a copy.
Other plugins, from other repositories
chrome-devtools-mcp
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer.
chrome-devtools-mcp
MCP configuration declaring 1 server: chrome-devtools.
firefox-devtools-troubleshoot
Diagnose and fix Firefox DevTools MCP setup issues. Use this if the firefox-devtools-mcp plugin is not working.
firefox-devtools-mcp
Control Firefox for browsing, web testing, and debugging. Fill forms, capture network and console activity, take screenshots, run scripts, and profile performance. Supports Android devices.
devharness
Run and debug a live app from inside Claude Code: breakpoints and variable inspection in Chrome and Node.js, managed dev servers, and replayable call history so setup is never re-driven by hand.
mobius-mcp
Scenario-focused skills for driving and debugging a running web app via the mobius-mcp MCP server — broken flows, QA walkthroughs, bug repros, perf stakeouts, and page audits.