Publisher · GitHub organization

browser-use

github.com/browser-use ↗Last audit 26 Oct 2026

browser-use publishes 1 MCP server and 9 agent skills on the atlas: 7 SAFE, 0 CAUTION, 3 BLOCK, with a mean score of 79/100. Every listing below is audited on its own.
Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “browser-use: skills and MCP servers”. Retrieved 26 Oct 2026. https://modelsatlas.com/orgs/browser-use
Listings
10

1 MCP servers · 9 skills

Mean score
79 / 100

mean of the audit scores

Findings
61

across all listings

Stars
781K

on the listed repositories

SAFE 7CAUTION 0BLOCK 3

Everything browser-use publishes here

Most stars first · stamps show the audited version

X402browser-use/browser-use
Skill ★ 119K
✓SAFEB · 89 · 26 Oct 2026
Remote Browserbrowser-use/browser-use
Skill ★ 119K
✓SAFEB · 89 · 24 Oct 2026
Qabrowser-use/browser-use
Skill ★ 119K
✓SAFEB · 89 · 23 Oct 2026
Open Sourcebrowser-use/browser-use
Skill ★ 119K
✓SAFEB · 89 · 22 Oct 2026
Cloudbrowser-use/browser-use
Skill ★ 119K
✕BLOCKD · 69 · 21 Oct 2026
Browser Usebrowser-use/browser-use
Skill ★ 119K
✓SAFEB · 89 · 20 Oct 2026
video-usebrowser-use/video-use
Skill ★ 29K
✓SAFEB · 89 · 20 Oct 2026
Browser Harness ♞browser-use/browser-harness
Skill ★ 19K
✕BLOCKF · 49 · 21 Oct 2026
Browser Harness ♞browser-use/browser-harness
Skill ★ 19K
✕BLOCKF · 47 · 20 Oct 2026
Vibetest Usebrowser-use/vibetest-use
MCP ★ 831
✓SAFEB · 89 · 27 Sep 2026

Questions

Are browser-use's MCP servers and skills safe to install?
Of 10 listings, 7 are SAFE, 0 CAUTION and 3 BLOCK, with a mean score of 79 out of 100. That is an average over separate audits: check each listing's own stamp before installing.
What does this page tell me about browser-use?
It collects every skill and MCP server on the atlas whose source lives under github.com/browser-use, with each one's verdict. It says nothing about who runs the organisation, and publisher identity is not verified here.
Can a publisher change its verdicts?
No. Each verdict comes from reading the source at a named commit. If a finding is wrong, report it with your reasoning on the listing's page and it is re-audited; the correction is public.

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.