Bash Vet Mcp

io.github.temurkhan13Published by GitHub account temurkhan13v1.0.3Updated Oct 24, 2026

Vet LLM-emitted shell commands BEFORE execution. 26 destructive-pattern rules / 8 families.

VerifiedSTDIODesktop onlyDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

A local MCP server that checks LLM-generated shell commands against destructive-pattern rules before they are executed.

What you can do
Vet shell commands produced by a language model before they run, using 26 destructive-pattern rules grouped into 8 families. Report which rules a candidate command matches so the assistant can flag risky commands. Intended as a pre-execution safety check rather than a command runner.
When to use it
Useful when an assistant proposes shell commands that will be run on a real machine and you want a rule-based check for destructive patterns before execution. Less relevant for read-only or sandboxed environments.
Requirements
Runs as a local process over stdio, installed from the PyPI package bash-vet-mcp, so a Python environment is needed. No authentication, environment variables or headers are declared.
Before you install
It only flags patterns it knows about; commands that match no rule are not guaranteed safe, so it should complement, not replace, human review and sandboxing. The manifest lists no tools, so confirm the actual interface after installing.

Installation

In SourceWeft

  1. Open Bash Vet Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

This repository has no README.

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.3LatestSep 16, 2026

Score

25% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.