retriEVAL

Overview

retriEVAL exposes LLM evaluation as MCP tools, letting any MCP-compatible AI assistant score outputs for faithfulness, relevancy, and hallucination. The model decides when to call these tools during conversation or agent runs, enabling built-in quality checks without leaving the assistant's context.

The server runs locally via Docker. Pull the image ghcr.io/hcarrillo001/retrieval-mcp:1.0.0 and run it with docker run -i --rm ghcr.io/hcarrillo001/retrieval-mcp:1.0.0. You'll need an API Key for authentication. The latest release is v1.0.0 under the Apache-2.0 license, with source code at hcarrillo001/retrieval-mcp on GitHub.

retrieVAL belongs in the AI & Agents category and integrates with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this server, claim this listing to verify ownership, earn the Verified badge, and keep your details up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "retrieval": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/hcarrillo001/retrieval-mcp:1.0.0"
      ]
    }
  }
}