Korext: AI Code Governance

Governance copilot for AI-assisted coding. 72 packs, 532 rules, proof bundles.

我该使用它吗

质量与安全性

A
描述质量
96%
模式完整度
89%
命名质量
100%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~521token 数(工具定义)
~764 B典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.41%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "governance": {
      "command": "npx",
      "args": [
        "korext"
      ]
    }
  }
}

可运行的软件包

npmkorext1.0.0stdio

远程端点

https://app.korext.com/api/mcpstreamable-http

它能做什么

工具清单

工具(5)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢get_directives(packId)

Get enriched policy directives and living standards for one or more policy packs. Returns rules with governance context (CWE, MITRE, regulatory references) for inference time enforcement.

输入模式

{
  "type": "object",
  "properties": {
    "packId": {
      "oneOf": [
        {
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      ],
      "description": "Policy pack ID or array of IDs (e.g. 'web', ['web', 'pci-dss-v1']). Defaults to 'web'."
    }
  }
}
🟢check_code(code, packId)

Check a code snippet against one or more policy packs. Returns violations with severity, governance context (CWE, MITRE, regulatory), and line numbers.

输入模式

{
  "type": "object",
  "properties": {
    "code": {
      "type": "string",
      "description": "The code snippet to check."
    },
    "packId": {
      "oneOf": [
        {
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      ],
      "description": "Policy pack ID or array of IDs. Defaults to 'web'."
    }
  },
  "required": [
    "code"
  ]
}
🟢list_packs(industry, region)

List available policy packs with industry and region tags.

输入模式

{
  "type": "object",
  "properties": {
    "industry": {
      "type": "string",
      "description": "Filter by industry (e.g. finance, healthcare, defense, aerospace, energy, technology)"
    },
    "region": {
      "type": "string",
      "description": "Filter by region (e.g. us, eu, uk, global)"
    }
  }
}
⚪generate_proof(code, packId, language, fileName)

Scan code against policy packs and generate a cryptographically signed proof bundle. Returns the bundle ID, decision (PASS/BLOCK), violation count, and verification URL.

输入模式

{
  "type": "object",
  "properties": {
    "code": {
      "type": "string",
      "description": "The code to scan."
    },
    "packId": {
      "oneOf": [
        {
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      ],
      "description": "Policy pack ID(s). Defaults to 'web'."
    },
    "language": {
      "type": "string",
      "description": "Programming language (typescript, python, etc.)"
    },
    "fileName": {
      "type": "string",
      "description": "File name for context"
    }
  },
  "required": [
    "code"
  ]
}
🟢get_proof(bundleId)

Retrieve an existing proof bundle by ID. Returns the decision, violations, packs, and verification status.

输入模式

{
  "type": "object",
  "properties": {
    "bundleId": {
      "type": "string",
      "description": "The proof bundle ID (kpb_...)"
    }
  },
  "required": [
    "bundleId"
  ]
}

社区

评价此服务器

证据

最近观测

已验证未记录版本5 个工具
已验证未记录版本5 个工具
已验证未记录版本5 个工具