TypeSafe Jev

Overview

TypeSafe Jev is a Model Context Protocol server that enables typed judgment operations with calibrated probability returns. Any MCP-compatible AI assistant can invoke TypeSafe Jev's tools directly, letting the model decide when to use them for asking, ranking, and checking judgments within conversations or agent workflows.

The server runs locally on your machine via the npm package jevcore-mcp, which communicates with MCP over stdio. Installation is simple: npx -y jevcore-mcp. No authentication or external credentials are needed—it works immediately after install. The latest release is v0.4.1.

TypeaSafe Jev is categorized as a Development tool on mcp.site and integrates with all MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and others. If you're the maintainer, claim this listing to verify ownership, earn a Verified badge, and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "typesafe_jev": {
      "command": "npx",
      "args": [
        "-y",
        "jevcore-mcp"
      ]
    }
  }
}