AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
io.github.jnMetaCode/shellward
https://github.com/jnMetaCode/shellward
STDIO
No auth required
Hosted endpoint — paste into any MCP client.
Configuration this server reads at startup.
Security mode: enforce (block + log) or audit (log only)
Locale: auto, zh, or en
Injection detection threshold 0-100 (lower = stricter)
Where to find authoritative docs and source for shellward.
Open MCP Agent Studio and connect this server to Claude, GPT, Gemini, DeepSeek and more — no install required.
Open Agent Studio