Bash Vet MCP server
Vet LLM-emitted shell commands BEFORE execution. 26 destructive-pattern rules / 8 families.
C65/100grade C
Adoption
New
35 downloads/wk
Reviews
Write oneNobody has reviewed Bash Vet yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Bash Vet tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
no findings
- Code scan7 source files scanned25/25
- –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
- Maintenancerepository not readable: repo not found3/15
- Maintainer identityno repository or website to verify2/10
Overall 65/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON
Install Bash Vet in Claude Code, Cursor or VS Code
claude mcp add bash-vet-mcp -- uvx bash-vet-mcp
Bash Vet: common questions
- Is Bash Vet MCP server safe?
- With care: it is graded C, so read the findings first (65/100). Read the Bash Vet safety report
- How do I install Bash Vet?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Bash Vet need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Bash Vet maintained?
- The latest release is v1.0.3.
- What can I use instead of Bash Vet?
- Servers from other publishers that do the same job: Decionis MCP server, Runapi MCP server and Shellward MCP server. Compare all Bash Vet alternatives.
Alternatives to Bash Vet
Same job from other publishers: the closest match first, then the best rated.
- DecionisAuthorize consequential AI agent actions before executionnot reviewedEstablishedA
- Runapi130+ AI models for image, video, music, and audio — 18 model families, one RunAPI account.not reviewedEstablishedA
- ShellwardAI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.not reviewedEstablishedA
- Roast My Design SystemAudit your Design System and serve your Agent the rules that keep AI-written UI on-system.not reviewedEstablishedA
- Roast My Design SystemAudit your Design System and serve your Agent the rules that keep AI-written UI on-system.not reviewedEstablishedA