RAGScore

Overview

RAGScore is a Model Context Protocol (MCP) server: Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM. Because it speaks the Model Context Protocol, AI assistants can use RAGScore as a set of callable tools instead of you copy-pasting between apps.

It runs locally: the Python package ragscore (via uvx) speaks MCP over stdio on your machine. The current release is v0.8.6, published under the Apache-2.0 license, with source at HZYAI/RagScore on GitHub, where it has earned 15 stars.

On mcp.site, RAGScore sits in the AI & Agents category. Any MCP client can use it — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed among them — via the install snippets below. If you maintain RAGScore for HZYAI, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "ragscore": {
      "command": "uvx",
      "args": [
        "ragscore"
      ]
    }
  }
}