Loading…
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.
sentinel-ai is an MCP server entry in ChatHome Skills, sourced from GitHub MCP Search and scored 23/100. Real-time AI safety guardrails for LLM apps. 10 scanners: prompt injection, PII, harmful content, code vulnerabilities, obfuscation detection. Sub-ms latency. P. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding sentinel-ai to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
git clone https://github.com/MaxwellCalkin/sentinel-ai.gitReview the upstream source before running this command.
Downloads a script and pipes it straight into a shell, executing remote code with no review.
curl -X POST http://localhost:8000/scan \
-H "Content-Type: application/json" \
-d '{"text": "Hello, world!"}'
```
Dispute this flag?Recursively force-deletes a root, home, or wildcard path — capable of wiping user data.
rm -rf /"Dispute this flag?Fetches an executable over plaintext HTTP (tamperable in transit) and runs it.
curl -X POST http://localhost:8000/scan \
-H "Content-Type: application/json" \
-d '{"text": "Hello, world!"}'
```
{
"fullName": "MaxwellCalkin/sentinel-ai"
}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.
Installs a Python package directly from a remote URL instead of PyPI.
pip install git+httpDispute this flag?Contains language that tries to override an agent's prior instructions (prompt injection).
Ignore all previous instructionsDispute this flag?Scan coverage: Install metadata and repository README.
Automated signals from install metadata and a bounded skill body — not a full code security audit and not a recursive source or dependency review.