MCP Tools DirectoryAbout this integration
Trust score for AI-generated code: scan repos, guard agent file writes, get a 0-100 score.
- Transport
- stdio
- Authentication
- none
- Initial setup
- none
- Runtime
- unattended
- Evidence
- documented
- Version
- 1.2.0
- Package
- @elberacasa/umbra
- Last compatibility test
- Not independently tested
Connect your agent
@elberacasa/umbraPublisher README and executable manifest reviewed offline; package and provider endpoints were not executed or independently security-audited. Qualification covers the MCP scan tools, not the package's separate setup, hook-installation, CI, or hosted badge operations.
Capabilities: Scan a repository for security and trust findings, Guard proposed content, Retrieve deterministic trust scores
Connected profiles
Additional details
io.github.elberacasa/umbra
Source ↗ · Checked 2026-09-171.2.0
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17npm
Source ↗ · Checked 2026-09-17@elberacasa/umbra
Source ↗ · Checked 2026-09-191.8.1
Source ↗ · Checked 2026-09-19Publisher documents a client-launched, non-interactive local MCP process. MCP-native clients launch the package's umbra-mcp binary with npx.
Source ↗ · Checked 2026-09-19The MCP scanning engine is documented as fully local and its MCP command includes no account or credential setting.
Source ↗ · Checked 2026-09-19MCP-native clients launch the package's umbra-mcp binary with npx.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19