servers / sentinel-ai

sentinel-ai

communityunknownlocalunknownhealthy

Real-time AI safety guardrails for LLM apps. 10 scanners: prompt injection, PII, harmful content, code vulnerabilities, obfuscation detection. Sub-ms latency. Python + TypeScript SDKs. MCP proxy. Claude Code hooks.

/ 100

01Tools · 0

Tools require a live tools/list handshake. For local/stdio servers that runs in a sandbox (gated off until configured); remote servers are probed directly.

02Install & source

No verified install method captured yet.

repohttps://github.com/MaxwellCalkin/sentinel-ai
homepagehttps://maxwellcalkin.github.io/sentinel-ai/
licenseApache-2.0
adoption19 stars · 3 forks

04Trust reasoning

0
Community server
official_status
+4
Commit within 6 months
maintenance
+2
19 stars
adoption
+3
Licensed: Apache-2.0
license

05Provenance & freshness

sourcesGitHub repo search [p4]

last_checked2026-06-18 17:50Z

next_check2026-06-20 17:50Z

cadenceevery 48h

verifiedmetadata:passed

index_statusindex — 6 unique facts >= 5

Next step

Generate a runtime config, or package this server into a governed Loadout with approvals and policies before your agent uses it.

Use in a Loadout