MCP stdio ShellGuard runs on your own machine — the client starts it, so there is no endpoint to ping. 70 installs a week from npm. Last commit 2 Nov 2026.
Defense-in-depth for MCP stdio servers: shell-injection guard, AST audit CLI, RCE blocking.
Today is the operative word: we check MCP stdio ShellGuard every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 stdio-shellguard -- npx -y mcp-stdio-shellguard
{
"mcpServers": {
"stdio-shellguard": {
"command": "npx",
"args": [
"-y",
"mcp-stdio-shellguard"
]
}
}
}
[mcp_servers.stdio-shellguard]
command = "npx"
args = ["-y", "mcp-stdio-shellguard"]
{
"mcpServers": {
"stdio-shellguard": {
"command": "npx",
"args": [
"-y",
"mcp-stdio-shellguard"
]
}
}
}
{
"servers": {
"stdio-shellguard": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-stdio-shellguard"
]
}
}
}
Audit AI agent configs for prompt injection & rogue MCP servers; vet packages
System-automation agent MCP server for opencode/claude/pi: guarded shell, dry-run-first, audited.
Guardrail for AI agents on SQL Server: statement blocking, optional read-only mode and an audit log.
Security scanner for MCP servers - detects tool poisoning and injection
Static blast-radius audit for MCP servers before agent install. Manifest optional.
Governance proxy for MCP servers: allowlist, forced dry run, human confirmation, blast radius, audit
MCP server for JWT decoding and inspection
Reference MCP stdio server for observing Vercel projects and deployments.
Answers built from our own checks of this server.