MCP Tools DirectoryAbout this integration
Precision-first security scanning for Model Context Protocol servers.
- Transport
- stdio
- Authentication
- none
- Initial setup
- none
- Runtime
- unattended
- Evidence
- documented
- Version
- 0.8.7
- Package
- mcp-guardian-scan
- Last compatibility test
- Not independently tested
Connect your agent
mcp-guardian-scanPublisher README and executable manifest reviewed from frozen captures. Documented only; package and integration endpoint were not executed or independently security-audited.
Capabilities: Scan MCP metadata, Apply static and semantic policy checks, Compare approved definition baselines, Return credential-safe findings
Connected profiles
Additional details
io.github.gentaArnezzi/mcpsentinel
Source ↗ · Checked 2026-09-170.8.7
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17pypi
Source ↗ · Checked 2026-09-17MCPSENTINEL_ALLOWED_HOSTS
Source ↗ · Checked 2026-09-17mcp-guardian-scan
Source ↗ · Checked 2026-09-190.8.7
Source ↗ · Checked 2026-09-19The mcpsentinel-mcp script exposes scan_mcp_server over local stdio.
Source ↗ · Checked 2026-09-19The default heuristic judge is fully offline and requires no API key; the optional OpenAI judge is not the default.
Source ↗ · Checked 2026-09-19Local installed launcher: mcpsentinel-mcp.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19