Is SUNGLASSES MCP server safe?
Probably. Read the findings first.
Use with care. Some checks failed or could not be verified.
What to know before installing
- highShell command built from a string (injection risk)
How SUNGLASSES compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 57/100
- higher than 14% of 4,460 AI and agents servers
Public scan report
scanner v0.1.10 · 2026-10-13 · same rubric, same numbers if you re-run it
1 high2 medium
- Code scan1500 source files scanned3/25
- –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 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner7/10
Findings (3)
- mediumeval / new Function used
exec.evalsunglasses-0.6.8/attack-db/attacks/agent-workflow-security/GLS-AW-048-guardrail-evaluation-fixture-tampering.json: …rge|rewrite|weaken|poison|mutate)\\s+(?:eval(?:uation)?|test|guardrail|benchmark|redt…
- highShell command built from a string (injection risk)
exec.shell-concatsunglasses-0.6.8/attack-db/attacks/command-injection/GLS-CI-004-unquoted-shell-interpolation-injection.json: …", "subprocess without shlex", "os.system(f", "shell=True", "subprocess.call…
- mediumsubprocess with shell=True
exec.shell-truesunglasses-0.6.8/attack-db/attacks/command-injection/GLS-CI-004-unquoted-shell-interpolation-injection.json: …without shlex", "os.system(f", "shell=True", "subprocess.call(f", "subproc…
Overall 57/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON
Other servers that do what SUNGLASSES does
- Basic MemoryLocal-first knowledge management with bi-directional LLM sync via Markdown files.not reviewedWidely usedB
- PaperBananaGenerate academic diagrams and statistical plots from text using multi-agent AI.not reviewedEstablishedA
- DecionisAuthorize consequential AI agent actions before executionnot reviewedEstablishedA