SeleniumBase MCP
by seleniumbase·
io.github.seleniumbase/seleniumbase·v4.54.9Stealthy browser automation, testing, and web-scraping via CDP Mode.
B83/100grade B
Adoption
Not measured yet
Usage numbers are collected on the next scan
Reviews
Write oneNobody has reviewed SeleniumBase MCP yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Tools
Tool lists for local packages are only visible after install.
Public scan report
scanner v0.1.2 · 2026-09-18 · same rubric, same numbers if you re-run it
2 medium
- Code scan128 source files scanned15/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- Tool poisoningonly the listing description was available15/15
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
Findings (2)
- mediumsubprocess with shell=True
exec.shell-trueseleniumbase-4.54.9/seleniumbase/behave/behave_sb.py: …struct a explicit argument list without shell=True cmd = ["behave", "-d"] + command_ar…
- mediumNetwork call to a raw IP address
net.raw-ipseleniumbase-4.54.9/seleniumbase/utilities/selenium_grid/grid_hub.py: …") print("Grid Hub Console: http://127.0.0.1:4444/grid/console") print("") …
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON
Install directly
claude mcp add seleniumbase -- uvx seleniumbase
Alternatives to SeleniumBase MCP
Same job, ranked by rating then adoption.
- ghostlightVisible local browser automation in signed-in Chromium, with optional policy and audit.not reviewed—A
- AIHawkAI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.not reviewed—A
- pdfMerge, split, extract, rotate, reorder and stamp PDF pages from your AI chat, all offline.not reviewed—A
- zipCreate, inspect and extract zip archives offline, with traversal, symlink and zip-bomb guards.not reviewed—A
- news-article-extractorExtract clean article text, titles, and metadata from news URLs - ready for NLP pipelines.not reviewed—A