io.github.Aitejiu/jev

not probeable (local package)

Unclaimed · Unverified

Publisher-provided description

Jev judgments for agents: injection scanning, shell risk gating, ranking

Summary by lookupd

Lets an agent scan text for prompt injection and gate shell commands by risk before running them.

Install

Claude Code, pypi package (stdio)

claude mcp add jev -- uvx jev-mcp

Codex, pypi package (stdio)

codex mcp add jev -- uvx jev-mcp

Cursor, pypi package (stdio) → .cursor/mcp.json

{
  "mcpServers": {
    "jev": {
      "command": "uvx",
      "args": [
        "jev-mcp"
      ]
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.Aitejiu/jev.svg)](https://lookupd.com/servers/io.github.Aitejiu/jev)