RAGScore MCP Server

Generate QA datasets & evaluate RAG systems. Privacy-first, any LLM, local or cloud.

Local serverstdioPython

What is the RAGScore MCP server?

Generate QA datasets & evaluate RAG systems. Privacy-first, any LLM, local or cloud. That is what the ragscore mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

🔒 Privacy-First • ⚡ Lightning Fast • 🤖 Any LLM • 🏠 Local or Cloud • 🌍 Multilingual

Getting it running

Installation goes through your MCP client rather than a global install: point it at ragscore on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

What it needs from you

Configuration is passed through the environment: OPENAI_API_KEY, ANTHROPIC_API_KEY, DASHSCOPE_API_KEY, LLM_BASE_URL, RAGSCORE_CHUNK_SIZE, RAGSCORE_QUESTIONS_PER_CHUNK, RAGSCORE_WORK_DIR, RAGSCORE_NO_TELEMETRY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. It is maintained by HZYAI; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

How to install the RAGScore MCP server

{
  "mcpServers": {
    "ragscore": {
      "command": "uvx",
      "args": ["ragscore"],
      "env": {
        "OPENAI_API_KEY": "your-value",
        "ANTHROPIC_API_KEY": "your-value",
        "DASHSCOPE_API_KEY": "your-value",
        "LLM_BASE_URL": "your-value",
        "RAGSCORE_CHUNK_SIZE": "your-value",
        "RAGSCORE_QUESTIONS_PER_CHUNK": "your-value",
        "RAGSCORE_WORK_DIR": "your-value",
        "RAGSCORE_NO_TELEMETRY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
OPENAI_API_KEYCredential the server authenticates with.Yes
ANTHROPIC_API_KEYCredential the server authenticates with.Yes
DASHSCOPE_API_KEYCredential the server authenticates with.Yes
LLM_BASE_URLEndpoint or connection string the server talks to.Yes
RAGSCORE_CHUNK_SIZEConfiguration value read at startup.Optional
RAGSCORE_QUESTIONS_PER_CHUNKConfiguration value read at startup.Optional
RAGSCORE_WORK_DIRFilesystem location the server is allowed to use.Optional
RAGSCORE_NO_TELEMETRYConfiguration value read at startup.Optional

Frequently asked questions

It connects RAGScore to MCP-compatible AI assistants such as Claude and Cursor. Instead of copying data back and forth by hand, the assistant works with RAGScore directly.