conKurrence
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 conkurrenceRelated 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 mcpClaude 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 |
| 在多个 AI 评估者之间执行评估 |
| 生成详细的 Markdown 报告 |
| 两次运行的并排比较 |
| 跟踪多次运行的一致性 |
| 基于你的数据的 AI 驱动模式建议 |
| 在运行前验证模式 |
| 估算成本和 Token 使用量 |
链接
主页: conkurrence.com
许可证
BUSL-1.1 — 商业源码许可证 1.1
This server cannot be deployed
Maintenance
Related MCP Connectors
LLM & RAG evals: hallucination, eval contracts, semantic tests, tokens & model info. Free, no key.
Checks if a cheaper model agrees with your GPT, Claude or Gemini outputs, and what routing saves.
MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.
Measure what ChatGPT, Claude, Gemini and 4 more AI engines say about any business. No auth.
Related MCP Servers
AlicenseNot gradedqualityCmaintenanceProvides 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.4Apache 2.0- AlicenseAqualityBmaintenancePrediction stability engine for AI agents. Evaluate model stability, detect ghosts, probe any LLM for instability, monitor fleet drift. 20 tools + 1 resource. Works with Claude, Cursor, VS Code.2020 npm1-
- AlicenseAqualityDmaintenanceMulti-AI Consensus Tool: Query multiple AI models in parallel, synthesize responses for better accuracy, and reduce AI bias through ensemble decision-making.133MIT

tokonomix-council-mcpofficial
AlicenseAqualityBmaintenanceEnables multi-model consensus decision-making for high-stakes AI decisions, using independent expert models and a judge to surface disagreements and ground decisions.11164 npm1MIT