AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs
io.github.sparkvibe-io/GuardianShield
https://github.com/sparkvibe-io/GuardianShield
STDIO
No auth required
Hosted endpoint — paste into any MCP client.
Configuration this server reads at startup.
Default safety profile (general, education, healthcare, finance, children)
Path to the SQLite audit database
Set to 1 for debug logging
Where to find authoritative docs and source for GuardianShield.
Open MCP Agent Studio and connect this server to Claude, GPT, Gemini, DeepSeek and more — no install required.
Open Agent Studio