Bash Vet MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 139 installs a week from pypi.
Vet LLM-emitted shell commands BEFORE execution. 26 destructive-pattern rules / 8 families.
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add bash-vet-mcp -- uvx bash-vet-mcp
{
"mcpServers": {
"bash-vet-mcp": {
"args": [
"bash-vet-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.bash-vet-mcp]
command = "uvx"
args = ["bash-vet-mcp"]
{
"mcpServers": {
"bash-vet-mcp": {
"args": [
"bash-vet-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"bash-vet-mcp": {
"args": [
"bash-vet-mcp"
],
"command": "uvx"
}
}
}
Safety checks an agent runs before it acts: package malware, destructive command, secret leak.
Sophisticated bash command MCP server that runs and manages shell execution.
MCP server for executing shell commands on remote hosts via SSH.
Secure code execution sandbox for Claude — run Python, JavaScript, and shell commands
Structural similarity-based code filter. Stops malicious code pattern reaching execution tools.
Modern SSH for AI agents — cloud servers to BusyBox routers, with destructive commands blocked.
Unified execution environment for Python code, shell commands, and programmatic MCP tool calls
Validate tool-call args before execution. Returns LLM-friendly retry hints.
Answers built from our own checks of this server.