Plato's Kallipolis

Read-only MCP tools for AI agent discovery, structured resources, and NIULAI information.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
62%
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

~1,212token 数(工具定义)
~1.7 KB典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 0.95%)

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": {
    "platos-kallipolis": {
      "url": "https://platoskallipolis.com/api/mcp"
    }
  }
}

远程端点

https://platoskallipolis.com/api/mcpstreamable-http

它能做什么

工具清单

工具(6)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢search_agents(capability, protocol)

Search the public agent registry by capability and protocol. Preview data only.

输入模式

{
  "type": "object",
  "properties": {
    "capability": {
      "type": "string",
      "description": "Capability identifier or substring"
    },
    "protocol": {
      "type": "string",
      "enum": [
        "any",
        "a2a",
        "mcp",
        "rest"
      ],
      "default": "any"
    }
  },
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "schema": {
      "type": "string"
    },
    "data": {
      "type": "array"
    },
    "provenance": {
      "type": "object"
    }
  },
  "required": [
    "schema",
    "data",
    "provenance"
  ]
}
🟢search_resources(category, q, limit, cursor)

Search 350 prepared structured resource profiles by category, keyword or declared source hostname without contacting external providers.

输入模式

{
  "type": "object",
  "properties": {
    "category": {
      "type": "string",
      "enum": [
        "agent-interoperability",
        "ai-discovery-and-registry",
        "ai-safety-provenance-and-audit",
        "data-knowledge-infrastructure",
        "enterprise-application-connectors",
        "platform-integration",
        "public-data-apis"
      ]
    },
    "q": {
      "type": "string",
      "minLength": 1,
      "maxLength": 100,
      "description": "Up to 8 whitespace-separated terms within 100 UTF-16 code units including outer whitespace; all terms must match literal case-insensitive substrings across public fields, declared publisher names or declared source hosts, in any order. Example: World Bank public, or worldbank.org public. Hostname matches include label-boundary subdomains; no full URLs, credentials, control characters, stemming or model inference. Ordering: exact resource ID first, then every term matched as a whole word in the title or a declared publisher name, or as a declared source host, then remaining substring matches; ties use stable resource ID order. Ranking is not a quality or ownership assertion."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "default": 25
    },
    "cursor": {
      "type": "integer",
      "minimum": 0,
      "maximum": 350,
      "default": 0
    }
  },
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "schema": {
      "type": "string"
    },
    "data": {
      "type": "array"
    },
    "page": {
      "type": "object"
    },
    "provenance": {
      "type": "object"
    },
    "boundaries": {
      "type": "object"
    }
  },
  "required": [
    "schema",
    "data",
    "page",
    "provenance",
    "boundaries"
  ]
}
🟢get_resource(resourceId)

Retrieve one complete prepared resource profile, including evidence-backed facts and primary-source provenance, by its stable resource ID.

输入模式

{
  "type": "object",
  "properties": {
    "resourceId": {
      "type": "string",
      "minLength": 1,
      "maxLength": 160,
      "pattern": "^[a-z0-9][a-z0-9._:-]{0,159}$"
    }
  },
  "required": [
    "resourceId"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "schema": {
      "type": "string"
    },
    "data": {
      "type": "object"
    },
    "provenance": {
      "type": "object"
    },
    "citation": {
      "type": "object"
    },
    "boundaries": {
      "type": "object"
    }
  },
  "required": [
    "schema",
    "data",
    "provenance",
    "citation",
    "boundaries"
  ]
}
🟢get_niulai_info

Return publisher-declared Base network, contract, claim, community-role, custody, and risk-boundary information for 牛来 (NIULAI).

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "schema": {
      "type": "string"
    },
    "symbol": {
      "type": "string"
    },
    "network": {
      "type": "object"
    },
    "contracts": {
      "type": "object"
    },
    "roles": {
      "type": "array"
    },
    "exclusions": {
      "type": "array"
    },
    "provenance": {
      "type": "object"
    }
  },
  "required": [
    "schema",
    "symbol",
    "network",
    "contracts",
    "roles",
    "exclusions",
    "provenance"
  ]
}
🟢get_growth_metrics

Return enabled, partial, contract-only, and unavailable growth metrics with privacy and interpretation boundaries.

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "schema": {
      "type": "string"
    },
    "metrics": {
      "type": "object"
    },
    "privacy": {
      "type": "object"
    },
    "interpretation": {
      "type": "object"
    }
  },
  "required": [
    "schema",
    "metrics",
    "privacy",
    "interpretation"
  ]
}
🟢compile_query_plan(intent, sources, freshness, evidence, limits, ...)

Normalize a public-data query into a typed evidence, freshness, latency, result, and cost plan. Compilation does not execute retrieval or contact providers.

输入模式

{
  "type": "object",
  "properties": {
    "intent": {
      "type": "string",
      "minLength": 3,
      "maxLength": 2000
    },
    "sources": {
      "type": "array",
      "minItems": 1,
      "maxItems": 16,
      "items": {
        "type": "object"
      }
    },
    "freshness": {
      "type": "object"
    },
    "evidence": {
      "type": "object"
    },
    "limits": {
      "type": "object"
    },
    "output": {
      "type": "object"
    },
    "policy": {
      "type": "object"
    }
  },
  "required": [
    "intent"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object",
  "properties": {
    "schema": {
      "type": "string"
    },
    "planId": {
      "type": "string"
    },
    "state": {
      "type": "string"
    },
    "executionAvailable": {
      "type": "boolean"
    },
    "plan": {
      "type": "object"
    },
    "provenance": {
      "type": "object"
    }
  },
  "required": [
    "schema",
    "planId",
    "state",
    "executionAvailable",
    "plan",
    "provenance"
  ]
}

社区

评价此服务器

证据

最近观测

已验证未记录版本6 个工具
已验证未记录版本6 个工具
已验证未记录版本6 个工具