Shellward runs on your own machine — the client starts it, so there is no endpoint to ping. 235 installs a week from npm. Last commit 9 Sep 2026.
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
We read the source, 20 h ago · rules 3dff92dd89df
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
- 危险命令(rm -rf /、格式化磁盘等)→ 已被代码层拦截
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const child = spawn(cmd, cmdArgs, { stdio: 'ignore', detached: true })
['.ssh/id_rsa', 0o600],
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Shellward and you get told the day something new turns up.
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 shellward -- npx -y shellward
{
"mcpServers": {
"shellward": {
"args": [
"-y",
"shellward"
],
"command": "npx"
}
}
}
[mcp_servers.shellward]
command = "npx"
args = ["-y", "shellward"]
{
"mcpServers": {
"shellward": {
"args": [
"-y",
"shellward"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"shellward": {
"args": [
"-y",
"shellward"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
SHELLWARD_MODE (Security mode: enforce (block + log) or audit (log only)), SHELLWARD_LOCALE (Locale: auto, zh, or en), SHELLWARD_THRESHOLD (Injection detection threshold 0-100 (lower = stricter)).
The author declared them in the registry entry; get the values from the project itself.
Security scanner for MCP servers - detects tool poisoning and injection
Security scanning and threat detection for AI agents
AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs
Security scanning and trust verification for AI agent tools.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening
Security scanning for AI coding tools. Detects secrets, threat models, and runs pre-commit checks.
Real-time semantic security for AI coding agents and MCP tools
Answers built from our own checks of this server.