MCPLow riskUnclaimed

RAGScore

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

HZYAIhzyai/ragscore★ 15Updated May 19, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.HZYAI/ragscore",
  "description": "Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.",
  "title": "RAGScore",
  "repository": {
    "url": "https://github.com/HZYAI/RagScore",
    "source": "github"
  },
  "version": "0.8.6",
  "packages": [
    {
      "registryType": "pypi",
      "identifier": "ragscore",
      "version": "0.8.6",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "OpenAI API key (if using OpenAI provider)",
          "format": "string",
          "isSecret": true,
          "name": "OPENAI_API_KEY"
        },
        {
          "description": "Anthropic API key (if using Anthropic provider)",
          "format": "string",
          "isSecret": true,
          "name": "ANTHROPIC_API_KEY"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—python
Installs—pypi:ragscore@0.8.6
Runs install scripts—None
NetworkNoneNone
Needs credentialsANTHROPIC_API_KEYOPENAI_API_KEYANTHROPIC_API_KEYOPENAI_API_KEY
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #10.8.6latestOct 7, 2026