Skip to main content
Glama

ConKurrence

一条命令。找出你的 AI 是否与自身达成一致。

ConKurrence 是一个用于 AI 评估流水线的统计验证一致性测量工具包。它使用多个 AI 模型作为独立评估者,通过 Fleiss' kappa 和自助法置信区间衡量评估者间的一致性,并将有争议的项目路由给人类专家。

安装

npm install -g conkurrence

Related MCP server: CI-1T Prediction Stability Engine

MCP 服务器

在 Claude Desktop 或任何兼容 MCP 的客户端中将 ConKurrence 用作 MCP 服务器:

npx conkurrence mcp

Claude Desktop 配置

添加到你的 claude_desktop_config.json

{
  "mcpServers": {
    "conkurrence": {
      "command": "npx",
      "args": ["-y", "conkurrence", "mcp"]
    }
  }
}

Claude Code 插件

/plugin marketplace add AlligatorC0der/conkurrence

功能

  • 多模型评估 — 同时针对 Bedrock、OpenAI 和 Gemini 模型运行你的模式

  • 统计严谨性 — 带有自助法置信区间的 Fleiss' kappa,用于验证的 Kendall's W

  • 自洽模式 — 无需 API 密钥;通过 MCP 采样使用宿主模型

  • 模式建议 — 基于你的数据进行 AI 驱动的模式设计

  • 趋势跟踪 — 比较不同时间的运行结果,检测一致性下降

  • 成本估算 — 在运行前了解成本

MCP 工具

工具

描述

conkurrence_run

在多个 AI 评估者之间执行评估

conkurrence_report

生成详细的 Markdown 报告

conkurrence_compare

两次运行的并排比较

conkurrence_trend

跟踪多次运行的一致性

conkurrence_suggest

基于你的数据的 AI 驱动模式建议

conkurrence_validate_schema

在运行前验证模式

conkurrence_estimate

估算成本和 Token 使用量

链接

许可证

BUSL-1.1 — 商业源码许可证 1.1

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

No tool schema history has been recorded yet.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    C
    maintenance
    Provides advanced evaluation tools for assessing AI safety, alignment, and performance of LLM outputs. Enables programmatic evaluation of quality, safety metrics like toxicity and PII detection, and operational metrics including carbon footprint and cost estimation.
    4
    Apache 2.0
  • A
    license
    A
    quality
    C
    maintenance
    An MCP server that audits LLM-as-judge evaluations, detecting judge drift across runs, measuring bias through controlled probes, and comparing judge agreement with human raters.
    6
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/AlligatorC0der/conkurrence'

If you have feedback or need assistance with the MCP directory API, please join our Discord server