Sortition Knowledge

Research and sources on sortition, citizens' assemblies and democratic reform.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
55%
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

~443token 数(工具定义)
~661 B典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.35%)

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": {
    "sortition-knowledge": {
      "url": "https://mcp.sortition.dk"
    }
  }
}

远程端点

https://mcp.sortition.dkstreamable-http

它能做什么

工具清单

工具(4)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢get_service_overview

Describe the purpose, scope and recommended use of the Sortition Knowledge MCP service.

输入模式

{
  "type": "object",
  "properties": {},
  "title": "get_service_overviewArguments"
}
🟢search_knowledge(query, limit)

Semantically search the Sortition knowledge base. Use this for questions about sortition, citizens' assemblies, citizens' chambers, democratic institutions and related reforms. Returns relevant source excerpts with document name, page and score.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "title": "Query",
      "type": "string"
    },
    "limit": {
      "default": 5,
      "title": "Limit",
      "type": "integer"
    }
  },
  "required": [
    "query"
  ],
  "title": "search_knowledgeArguments"
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Result",
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "title": "search_knowledgeOutput"
}
🟢list_documents

List the source documents currently available in the Sortition knowledge base.

输入模式

{
  "type": "object",
  "properties": {},
  "title": "list_documentsArguments"
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Result",
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "title": "list_documentsOutput"
}
🟢get_document_page(document, page)

Retrieve the complete text of one page from a PDF source document. Use this after search_knowledge() when more context or source verification is needed.

输入模式

{
  "type": "object",
  "properties": {
    "document": {
      "title": "Document",
      "type": "string"
    },
    "page": {
      "title": "Page",
      "type": "integer"
    }
  },
  "required": [
    "document",
    "page"
  ],
  "title": "get_document_pageArguments"
}

社区

评价此服务器

证据

最近观测

已验证未记录版本4 个工具