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 10
- 2 8
- 1 1
Trust in production
- Trust it - 0%
- With caveats - 41%
- Wouldn't - 59%
23% would recommend this server
How reviewers scored it
- Setup & docs 2.6
- Auth experience 2.7
- Reliability 2.8
- Maintainer responsiveness 3.7
Why it got a C
Popular and very active; its one past CVE (an allowed-domains bypass, CVE-2025-47241) was fixed the same day. Biggest deduction: there is no authentication at all, so whatever starts it gets full control of a real browser and its logged-in sessions. The model can also run code: the agent tool executes JavaScript in pages, and the --cli-mcp mode listed in the MCP Registry runs any Python on your machine. Stay on --mcp, set an allowlist, and run it isolated, because open reports say allowed_domains misses redirects.
How to connect
// ~/.cursor/mcp.json
{ "mcpServers": { "browser-use": { "command": "uvx",
"args": ["--from", "browser-use[cli]", "browser-use", "--mcp"],
"env": { "OPENAI_API_KEY": "your-openai-api-key-here" } } } }claude mcp add browser-use -- uvx --from 'browser-use[cli]' browser-use --mcp// claude_desktop_config.json
{ "mcpServers": { "browser-use": { "command": "uvx",
"args": ["--from", "browser-use[cli]", "browser-use", "--mcp"],
"env": { "OPENAI_API_KEY": "your-openai-api-key-here" } } } }Is browser-use MCP safe?
Is browser-use MCP safe to use?
browser-use 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 browser-use 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 browser-use 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 Chrome DevTools MCPLet an agent drive and debug a live Chrome with DevTools, including performance traces, network, console, screenshots, and scripts.
- C Playwright MCPDrive a real browser to navigate, click, fill, and extract via MCP.
Embed this badge
[](https://trustedmcp.io/servers/browser-use-mcp)<a href="https://trustedmcp.io/servers/browser-use-mcp"><img src="https://trustedmcp.io/badge/browser-use-mcp.svg" alt="TrustedMCP grade C" height="80"></a>Community reviews
Decent, not set-and-forget
It does the job, but it took some tweaking. No access control at all, it runs with my permissions. Fine on my laptop, not on a shared box. Fine in production if you sandbox it.
Used for Monitoring a competitor changelog
- Setup & docs 3/5
- Auth experience 4/5
- Reliability 3/5
- Maintainer responsiveness 4/5
Handy for dev, careful in prod
Useful tool, though I would not hand it to a junior unsupervised. Filed an issue and got a reply within two days. There is no auth layer, so whatever can reach it can use it. I keep it local only. It drives a real browser, so I give it a separate profile with no saved logins. Keeping it to local experiments for now.
Used for Monitoring a competitor changelog
- Setup & docs 3/5
- Auth experience 3/5
- Reliability 3/5
- Maintainer responsiveness 5/5
Too many sharp edges
It works in a demo, but things got shaky under real use. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list. Runs locally over stdio, so startup is instant and nothing leaves my machine unless a tool calls out.
Used for Visual regression checks
- Setup & docs 2/5
- Auth experience 3/5
- Reliability 2/5
- Maintainer responsiveness 3/5
OK for read-only work
Mostly reliable, with the odd timeout. 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 Monitoring a competitor changelog
- Setup & docs 3/5
- Auth experience 4/5
- Reliability 3/5
- Maintainer responsiveness 4/5
Promising, a bit raw
Works well enough for what I need. You can tell it is actively maintained, the rough edges keep getting fixed.
Used for Scraping public pricing pages
- Setup & docs 3/5
- Auth experience 3/5
- Reliability 4/5
- Maintainer responsiveness 4/5
Too much access for my comfort
Gave it a fair shot over two weeks. Releases come often and the changelog is clear. There is no auth layer, so whatever can reach it can use it. I keep it local only.
Used for Scraping public pricing pages
- Setup & docs 2/5
- Auth experience 2/5
- Reliability 2/5
- Maintainer responsiveness 3/5
Fine for a demo, not for prod
Not what I expected from the description. Local stdio process, easy to start and stop from the client.
Used for Collecting screenshots for bug reports
- Setup & docs 2/5
- Auth experience 2/5
- Reliability 2/5
- Maintainer responsiveness 3/5
Exactly what I needed from browser-use
I use this almost daily. It drives a real browser, so I give it a separate profile with no saved logins. Releases come often and the changelog is clear. Keep permissions tight and it is a good tool.
Used for Collecting screenshots for bug reports
- Setup & docs 4/5
- Auth experience 2/5
- Reliability 3/5
- Maintainer responsiveness 4/5
Good, but read the permissions first
Good for experimenting, still deciding about production. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list. You can tell it is actively maintained, the rough edges keep getting fixed. It drives a real browser, so I give it a separate profile with no saved logins.
Used for Filling repetitive web forms
- Setup & docs 3/5
- Auth experience 2/5
- Reliability 3/5
- Maintainer responsiveness 4/5
Fast-moving, but no auth and broad local capability
The project moves quickly and the high-level API is nice. But there is no built-in access control and it has wide local capability — only sensible to run fully isolated. Pin the version, the API changes between releases.
Used for Evaluated for a research agent
- Setup & docs 3/5
- Auth experience 1/5
- Reliability 3/5
- Maintainer responsiveness 4/5
Would not run this unattended
Ran into problems pretty quickly. Filed an issue and got a reply within two days. Local stdio process, easy to start and stop from the client. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list.
Used for Research agent browsing documentation
- Setup & docs 1/5
- Auth experience 3/5
- Reliability 2/5
- Maintainer responsiveness 3/5
Struggled to get it stable
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 QA smoke tests after deploys
- Setup & docs 2/5
- Auth experience 2/5
- Reliability 2/5
- Maintainer responsiveness 3/5
Security story needs work
Ran into problems pretty quickly. It drives a real browser, so I give it a separate profile with no saved logins. Updates land regularly, and nothing broke when I upgraded. There is no auth layer, so whatever can reach it can use it. I keep it local only. For anything real I would look elsewhere.
Used for Collecting screenshots for bug reports
- Setup & docs 2/5
- Auth experience 3/5
- Reliability 2/5
- Maintainer responsiveness 3/5
Good in a throwaway VM, nowhere else
Inside a disposable VM with no credentials it is productive and I trust it there. The moment it can reach anything real, the no-auth design rules it out.
Used for Isolated VM doing web research tasks
- Setup & docs 3/5
- Auth experience 2/5
- 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. Keeping it to local experiments for now.
Used for End-to-end test runs against staging
- Setup & docs 2/5
- Auth experience 3/5
- Reliability 2/5
- Maintainer responsiveness 2/5
Solid core, fiddly setup
Some tools are great, a couple feel half finished. It drives a real browser, so I give it a separate profile with no saved logins. Local stdio process, easy to start and stop from the client. Worth it, just do not skip the hardening steps.
Used for End-to-end test runs against staging
- Setup & docs 3/5
- Auth experience 3/5
- Reliability 3/5
- Maintainer responsiveness 4/5
No complaints after a month
Installed it on a Friday, it was part of my workflow by Monday. Updates land regularly, and nothing broke when I upgraded. There is no auth layer, so whatever can reach it can use it. I keep it local only.
Used for End-to-end test runs against staging
- Setup & docs 4/5
- Auth experience 4/5
- Reliability 5/5
- Maintainer responsiveness 4/5
Does the job, docs could be better
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. I will check back in a few releases.
Used for Research agent browsing documentation
- Setup & docs 3/5
- Auth experience 3/5
- Reliability 3/5
- Maintainer responsiveness 5/5
Mixed feelings after two weeks
Took longer to configure than I expected. Runs locally over stdio, so startup is instant and nothing leaves my machine unless a tool calls out. 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 4/5
- Maintainer responsiveness 4/5
Needs more maintenance love
Setup was rough and the result was flaky. There is no auth layer, so whatever can reach it can use it. I keep it local only. I will check back in a few releases.
Used for Visual regression checks
- Setup & docs 3/5
- Auth experience 2/5
- Reliability 2/5
- Maintainer responsiveness 4/5
Capable but needs guardrails
Took longer to configure than I expected. 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 2/5
- Auth experience 4/5
- Reliability 3/5
- Maintainer responsiveness 5/5
Went back to calling the API directly
Setup was rough and the result was flaky. Updates land regularly, and nothing broke when I upgraded. 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. Not something I would put in production yet.
Used for Filling repetitive web forms
- Setup & docs 1/5
- Auth experience 2/5
- Reliability 1/5
- Maintainer responsiveness 2/5
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.