Our grade: 4 checks
Based on public data, not a full audit. See how we grade. Something changed? Request a re-grade.
Community rating
- 5 0
- 4 3
- 3 3
- 2 9
- 1 0
Trust in production
- Trust it - 0%
- With caveats - 53%
- Wouldn't - 47%
33% would recommend this server
How reviewers scored it
- Setup & docs 2.5
- Auth experience 2.5
- Reliability 2.5
- Maintainer responsiveness 3.5
Why it got a C
First-party from Google's Chrome DevTools team, with releases almost every week. Four 2026 advisories, including October's CVE-2026-106484, were all fixed before they were published (use 1.5.0 or later). By default it sends usage statistics, and CrUX lookups for performance traces, to Google. Biggest deduction: there is no authentication, and by default the model can run any JavaScript in a browser profile that keeps your logins and can open local files. Use --isolated, and --no-javascript-evaluation if you don't need scripts.
How to connect
// Cursor Settings > MCP > New MCP Server
{ "mcpServers": { "chrome-devtools": { "command": "npx",
"args": ["-y", "chrome-devtools-mcp@latest"] } } }
code --add-mcp '{"name":"io.github.ChromeDevTools/chrome-devtools-mcp","command":"npx","args":["-y","chrome-devtools-mcp"],"env":{}}'
claude mcp add chrome-devtools --scope user npx chrome-devtools-mcp@latest
// claude_desktop_config.json
{ "mcpServers": { "chrome-devtools": { "command": "npx",
"args": ["-y", "chrome-devtools-mcp@latest"] } } }
Is Chrome DevTools MCP safe?
Is Chrome DevTools MCP safe to use?
Chrome DevTools MCP grades C (usable with care). There is no login: anything that can start or reach it gets its full access. It can run model-controlled code or uses a plaintext remote connection, so run it isolated with no credentials.
Does Chrome DevTools MCP have known vulnerabilities?
Not in our current data: it has no open CVEs or advisories. We re-check as new ones are published.
Does Chrome DevTools MCP support authentication?
No. It has no login of its own, so limit who and what can start it.
Alternatives in Browser & Web Automation
- A Apify MCP ServerOfficial Apify server to find and run thousands of ready-made scrapers and automation Actors, then read their results.
- C BrowserTools MCPGive your coding agent the console logs, network requests, screenshots and Lighthouse audits from the Chrome tab you already have open.
- C Playwright MCPDrive a real browser to navigate, click, fill, and extract via MCP.
- C browser-use MCPLLM-oriented browser automation with a high-level action API.
Community reviews
Useful, with a few rough edges
I like it, with reservations. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list. It drives a real browser, so I give it a separate profile with no saved logins.
Used for QA smoke tests after deploys
- Setup & docs 3/5
- Auth experience 3/5
- Reliability 2/5
- Maintainer responsiveness 4/5
Fine for a demo, not for prod
Setup was rough and the result was flaky. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list. Filed an issue and got a reply within two days. Worth it, just do not skip the hardening steps.
Used for Filling repetitive web forms
- Setup & docs 2/5
- Auth experience 2/5
- Reliability 2/5
- Maintainer responsiveness 3/5
Good defaults, good docs
Of the Chrome DevTools integrations I tried, this one is the most predictable. No access control at all, it runs with my permissions. Fine on my laptop, not on a shared box. Local stdio process, easy to start and stop from the client. I would use it in prod, but only with a human approving writes.
Used for Scraping public pricing pages
- Setup & docs 4/5
- Auth experience 3/5
- Reliability 4/5
- Maintainer responsiveness 4/5
Not ready for anything that matters
Not what I expected from the description. No access control at all, it runs with my permissions. Fine on my laptop, not on a shared box. It drives a real browser, so I give it a separate profile with no saved logins. Filed an issue and got a reply within two days. I will check back in a few releases.
Used for End-to-end test runs against staging
- Setup & docs 2/5
- Auth experience 2/5
- Reliability 2/5
- Maintainer responsiveness 4/5
Easy win for our agent setup
Clear tool names, sensible outputs, very few surprises. No access control at all, it runs with my permissions. Fine on my laptop, not on a shared box. Keep permissions tight and it is a good tool.
Used for End-to-end test runs against staging
- Setup & docs 3/5
- Auth experience 4/5
- Reliability 4/5
- Maintainer responsiveness 5/5
Needs more maintenance love
Gave it a fair shot over two weeks. There is no auth layer, so whatever can reach it can use it. I keep it local only. Recommended, with sensible guardrails.
Used for Monitoring a competitor changelog
- Setup & docs 2/5
- Auth experience 2/5
- Reliability 2/5
- Maintainer responsiveness 2/5
Handy for dev, careful in prod
It does the job, but it took some tweaking. It drives a real browser, so I give it a separate profile with no saved logins.
Used for Monitoring a competitor changelog
- Setup & docs 3/5
- Auth experience 3/5
- Reliability 4/5
- Maintainer responsiveness 5/5
Mixed feelings after two weeks
Good for experimenting, still deciding about production. There is no auth layer, so whatever can reach it can use it. I keep it local only.
Used for Research agent browsing documentation
- Setup & docs 3/5
- Auth experience 3/5
- Reliability 3/5
- Maintainer responsiveness 3/5
Too much access for my comfort
Ran into problems pretty quickly. You can tell it is actively maintained, the rough edges keep getting fixed. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list. Keeping it to local experiments for now.
Used for Research agent browsing documentation
- Setup & docs 2/5
- Auth experience 2/5
- Reliability 2/5
- Maintainer responsiveness 3/5
Struggled to get it stable
It works in a demo, but things got shaky under real use. It drives a real browser, so I give it a separate profile with no saved logins. For anything real I would look elsewhere.
Used for Scraping public pricing pages
- Setup & docs 2/5
- Auth experience 2/5
- Reliability 2/5
- Maintainer responsiveness 2/5
Went back to calling the API directly
I wanted to like this one. It drives a real browser, so I give it a separate profile with no saved logins. For anything real I would look elsewhere.
Used for Visual regression checks
- Setup & docs 2/5
- Auth experience 3/5
- Reliability 2/5
- Maintainer responsiveness 3/5
Too many sharp edges
It works in a demo, but things got shaky under real use. Releases come often and the changelog is clear. It drives a real browser, so I give it a separate profile with no saved logins. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list. Not something I would put in production yet.
Used for Collecting screenshots for bug reports
- Setup & docs 2/5
- Auth experience 2/5
- Reliability 1/5
- Maintainer responsiveness 4/5
Security story needs work
Ran into problems pretty quickly. You can tell it is actively maintained, the rough edges keep getting fixed.
Used for QA smoke tests after deploys
- Setup & docs 1/5
- Auth experience 3/5
- Reliability 1/5
- Maintainer responsiveness 3/5
Better than the DIY script it replaced
Started with it as an experiment, now it is a fixture. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list. It drives a real browser, so I give it a separate profile with no saved logins. Fine in production if you sandbox it.
Used for Visual regression checks
- Setup & docs 4/5
- Auth experience 3/5
- Reliability 3/5
- Maintainer responsiveness 4/5
Would not run this unattended
Not what I expected from the description. There is no auth layer, so whatever can reach it can use it. I keep it local only. Keeping it to local experiments for now.
Used for Filling repetitive web forms
- Setup & docs 3/5
- Auth experience 1/5
- Reliability 3/5
- Maintainer responsiveness 4/5
Write a review
Ran this server? Tell other teams how it went. You get one review per server. We email you a link to confirm it, then an editor checks it before it goes up. We never show your email.