MCP Tools DirectoryAbout this integration
Exposes documented TypeSafe Jev judgments for prompt-injection scanning, shell-risk gating, and candidate ranking.
- Transport
- stdio
- Authentication
- api-key
- Initial setup
- credentials
- Runtime
- unattended
- Evidence
- documented
- Package
- jev-mcp
- Last compatibility test
- Not independently tested
Connect your agent
jev-mcpThe documented stdio server calls an external TypeSafe service using a configured API key. The package, service, and benchmark claims were not executed or independently security-audited.
Capabilities: Scan tool, web, and email output for prompt-injection instructions, Score shell-command risk across destructive, secret, exfiltration, and irreversibility dimensions, Rank candidate passages by relevance for retrieval workflows
Connected profiles
Additional details
jev-mcp
Source ↗ · Checked 2026-09-220.1.2
Source ↗ · Checked 2026-09-22The server has a documented stdio runtime and can be launched by an MCP client through the packaged command.
Source ↗ · Checked 2026-09-22A TYPESAFE_API_KEY environment credential is required for the documented integration.
Source ↗ · Checked 2026-09-22Configure the MCP client to launch jev-mcp through uvx and provide TYPESAFE_API_KEY in the child environment.
Source ↗ · Checked 2026-09-22Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-22