Is Watch Skill MCP server safe?

Yes, with the usual care.

B77/100grade B

Safe to use. Minor gaps such as a missing repository or slower maintenance.

No critical or high findings in the latest scan.

How Watch Skill compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 77/100; higher than 50% of 4,460 AI and agents servers
Tools that change things: 5%; typical: 0%. Fewer write tools means less an agent can break

What its tools let an agent do: 33 read · 1 create · 1 change · 1 delete · 3 run or deploy

scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it

2 medium

Code scan205 source files scanned15/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitylocal package, no credentials required12/15
Maintenancelast push 2 days ago15/15
Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

mediumsubprocess with shell=Trueexec.shell-true

watch_skill-1.4.3/src/watch_skill/loop/framework.py: …sult = subprocess.run( cmd, shell=True, capture_output=True, text=True, …

mediumeval / new Function usedexec.eval

watch_skill-1.4.3/src/watch_skill/vision/worker_main.py: …_mem_usage=True, local_files_only=True).eval() STATE.model, STATE.processor = mo…

Overall 77/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

Claude Real Video
Let any LLM watch a video locally — and search everything it has ever watched.
not reviewed
Established
A
WaveSpeed
Run any model on the live WaveSpeed catalog: image, video, audio, 3D.
not reviewed
Established
A
Watch CLI
Hand any social video to your AI agent — frames + transcript bundled. MCP server for watch-cli.
not reviewed
Established
B