MCP低风险未认领

agent-eval

Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.

RudrenduPaulrudrendupaul/agent-eval更新于 2026年8月10日

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.RudrenduPaul/agent-eval",
  "description": "Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.",
  "repository": {
    "url": "https://github.com/RudrenduPaul/agent-eval",
    "source": "github"
  },
  "version": "0.1.8",
  "packages": [
    {
      "registryType": "pypi",
      "identifier": "agent-regress-cli",
      "version": "0.1.8",
      "runtimeHint": "uvx",
      "transport": {
        "type": "stdio"
      },
      "runtimeArguments": [
        {
          "value": "agent-regress-cli",
          "type": "named",
          "name": "--from"
        }
      ],
      "packageArguments": [
        {
          "value": "agent-regress-mcp",
          "type": "positional",
          "valueHint": "script_name"
        }
      ]
    }
  ]
}

权限

声明检测
运行代码—python
安装—pypi:agent-regress-cli@0.1.8
安装时运行脚本—无
网络无无
需要的凭据无无
工作区外的路径—无
智能体工具—无

检查

低风险 · 没有发现需要提醒的地方。

未经人工审核 · 已做规则检查;模型审核尚未开启。

版本

  1. #10.1.8最新2026年10月7日