Loomal

RAGScore

MCP server by github.com/hzyai/ragscore

Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.

32 starspypi: ragscore

About RAGScore

RAGScore is an MCP (Model Context Protocol) server published by hzyai in the official MCP registry, listed under RAG Systems on Loomal. Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.

It ships as a Python package on PyPI (ragscore), so any MCP client that can launch a local process can run it.

Development happens in the open at github.com/hzyai/ragscore, where the project has earned 32 GitHub stars.

Use RAGScore with your agent

Claude Code · one command
claude mcp add ragscore -- uvx ragscore
Claude Desktop, Cursor & other MCP clients · config
{
  "mcpServers": {
    "ragscore": {
      "command": "uvx",
      "args": [
        "ragscore"
      ]
    }
  }
}
pypiragscore

Frequently asked questions

What is RAGScore?
RAGScore is an MCP (Model Context Protocol) server by hzyai in the RAG Systems category. Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.
How do I connect RAGScore to Claude, Cursor, or another MCP client?
Install RAGScore from its pypi package (ragscore) and register it under "mcpServers" in your client's MCP configuration — for example claude_desktop_config.json or Cursor's mcp.json — then restart the client.
Is RAGScore open source?
Yes — the source code is public at github.com/hzyai/ragscore, with 32 GitHub stars.
Can AI agents pay to use RAGScore?
Not yet through Loomal — RAGScore is listed as a free directory entry. If its maintainer verifies ownership, they can set per-call USDC pricing that agents pay over x402, with settlement on Base.

Listing data from the official MCP registry and GitHub, refreshed periodically. Not affiliated with the maintainer unless claimed. Maintain RAGScore? Claim this listing free by verifying GitHub ownership, or contact us.