Is Contextual MCP server safe?
Yes, with the usual care.
Safe to use. Minor gaps such as a missing repository or slower maintenance.
No critical or high findings in the latest scan.
Public scan report
scanner v0.1.9 · 2026-09-20 · same rubric, same numbers if you re-run it
2 medium
- Code scan232 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 8 days ago15/15
- Maintainer identityregistry namespace matches repository owner7/10
Findings (2)
- mediumsubprocess with shell=True
exec.shell-truecontextual_engine-1.0.2/contextual/mcp/tools/semantic.py: …r shell safety (passed as list arg, not shell=True) if target == "WORKING"…
- mediumeval / new Function used
exec.evalcontextual_engine-1.0.2/eval/manifest.yml: …too small for realistic retrieval eval (this was flagged as a possible risk in b…
Overall 75/100. 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 Contextual does
- NexusmemLocal-first memory for AI coding agents: shell history with exit codes, git diffs, docs, MCP.not reviewedGrowingA
- Agent MemoryGit-native project memory for AI coding agents: Markdown source of truth, reviewable, secret-safe.not reviewedGrowingA
- KindexPersistent knowledge graph and MCP server for AI workflows with git-tracked project context.not reviewedGrowingA
