Is DOS — the trust substrate for agent fleets 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 DOS — the trust substrate for agent fleets 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: 0%; typical: 0%. Fewer write tools means less an agent can break

What its tools let an agent do: 13 read

scanner v0.1.9 · 2026-09-25 · same rubric, same numbers if you re-run it

2 medium

Code scan233 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 5 days ago15/15
Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

mediumsubprocess with shell=Trueexec.shell-true

dos_kernel-0.30.0/src/dos/drivers/llm_judge.py: … return None try: # shell=True so an operator can set a full `claude -…

mediumeval / new Function usedexec.eval

dos_kernel-0.30.0/src/dos/intervention_eval.py: …d `arg_provenance` shipped a *detector* eval (precision/recall over minted-vs-resolved…

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

Basic Memory
Local-first knowledge management with bi-directional LLM sync via Markdown files.
not reviewed
Widely used
B
Agent-Native Plan
Structured visual plans and PR recaps with diagrams, prototypes, annotations, and sharing
not reviewed
Established
A
Watch Skill
Watch video and live sessions, keep timestamped evidence, and verify an agent's own work.
not reviewed
Established
B