Neuronto ARD Registry: Agentic Resource Discovery (ARD) Index

Neuronto ARD Registry: one search across every public ARD registry + 200,000+ verified MCP tools

我該用這個嗎

品質與安全性

A
說明品質
100%
結構描述完整度
78%
命名品質
95%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

根據工具定義與協定合規性的自動化分析。

上下文成本

~983Token(工具定義)
~1.5 KB典型回應大小
中等的注意力影響(128k 上下文的 0.77%)

這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。

安裝

一鍵安裝

將以下內容加入你的 `claude_desktop_config.json` 檔案:

{
  "mcpServers": {
    "agents-tools-search-discovery-ard-registry": {
      "url": "https://neuronto.com/mcp"
    }
  }
}

遠端端點

https://neuronto.com/mcpstreamable-http

它能做什麼

工具清單

工具(4)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢find_resource(query, kind, limit, federate, payment, ...)

Search for an MCP server, skill, agent, API or other callable capability for a task, across this index and every other public ARD registry at once. Returns ranked matches with a relevance score, the endpoint to connect to, and which registries carry each result. The score is relevance only and is not a trust or safety rating. Filter by payment (free, payable, x402, mpp) and a maximum price per call: terms come from the publisher's manifest or the endpoint's own 402 answer, and the caller pays the provider directly.

輸入結構描述

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "The task, in plain language. For example: 'scrape a website behind cloudflare'."
    },
    "kind": {
      "type": "string",
      "enum": [
        "any",
        "mcp-server",
        "skill",
        "a2a-agent",
        "agent",
        "webmcp",
        "plugin",
        "openapi",
        "graphql",
        "dataset",
        "package",
        "doc",
        "catalog",
        "registry"
      ],
      "description": "Restrict to one family of resource. Matching is normalised, so 'mcp-server' finds them under every media type in circulation, and 'a2a-agent' or 'agent' both reach A2A cards and ACP, OASF and AgentFacts descriptors. 'webmcp' is browser-page tools, which are not callable servers.",
      "default": "any"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 8
    },
    "federate": {
      "type": "boolean",
      "default": true,
      "description": "Also query upstream registries live and fuse the rankings. Off is faster."
    },
    "payment": {
      "type": "string",
      "enum": [
        "any",
        "free",
        "payable",
        "x402",
        "mpp",
        "card"
      ],
      "default": "any",
      "description": "Keep only resources with this payment requirement. 'free' means none is known; 'payable' means a price or a 402 is known."
    },
    "max_price_per_call": {
      "type": "number",
      "minimum": 0,
      "description": "Most you will pay for one call, in US dollars. A resource whose price is unknown is excluded."
    },
    "network": {
      "type": "string",
      "description": "Payment network, for example base, solana, tempo or stripe."
    }
  },
  "required": [
    "query"
  ]
}
🟢find_tool(query, limit, with_schema)

Search individual MCP tools by name and behaviour, not the servers that host them. Every tool returned here was read back from a live server's tools/list, so the name and input schema are what the server actually exposes rather than what its description claims. Use this when you know the shape of the call you need; use find_resource when you are looking for a service.

輸入結構描述

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "What the tool should do. For example: 'extract text from a pdf'."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 10
    },
    "with_schema": {
      "type": "boolean",
      "default": false,
      "description": "Include each tool's full JSON input schema. Verbose; off by default."
    }
  },
  "required": [
    "query"
  ]
}
🟡publish_resource(endpoint, domain)

List an MCP server or an ARD-publishing domain in this index so other agents can discover it. Give `endpoint` for an MCP server URL, or `domain` for a site that serves an ARD manifest. The submission is verified before it is indexed: an endpoint must complete an MCP initialize handshake, and a domain must serve a manifest that parses. Nothing is taken on trust, so a listing that succeeds here is one an agent can actually call.

輸入結構描述

{
  "type": "object",
  "properties": {
    "endpoint": {
      "type": "string",
      "description": "Absolute URL of an MCP server, e.g. https://example.com/mcp"
    },
    "domain": {
      "type": "string",
      "description": "A domain serving /.well-known/ard.json, e.g. example.com"
    }
  }
}
🟢registry_stats

How large this index is, what it holds, how much of it has been verified by introspection, and which upstream registries are federated.

輸入結構描述

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

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本4 個工具