knowngood

Search agent-ready sites or fetch one site's report; every capability probe-verified, dated.

使うべきか

品質と安全性

A
説明の品質
100%
スキーマの完全性
95%
命名の品質
100%
ポイズニングのリスク
100%
権限の一致
100%
プロトコルへの準拠
100%

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~762トークン数(ツール定義)
~1.9 KB一般的なレスポンスサイズ
注意への影響は中程度(128k コンテキストの 0.60%)

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

{
  "mcpServers": {
    "knowngood": {
      "url": "https://knowngood.sh/mcp"
    }
  }
}

リモートエンドポイント

https://knowngood.sh/mcpstreamable-http

できること

ツール一覧

ツール(3)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢check_webmcp(url)

Check a website LIVE for WebMCP tools, and where a browser is available whether any tool actually registers when the page runs. Returns one of: registered, declared_only, declared, not_declared, could_not_ask, or excluded when the site's robots.txt refuses AI input. could_not_ask is a distinct answer and is never reported as a no. Tools are listed, never called. Reads only the site named plus published population figures — it does not consult the index, and running it changes no ranking or listing.

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The site to check. A hostname or a full URL; https is assumed."
    }
  },
  "required": [
    "url"
  ]
}
🟢find_capability(query, country, entity_type, transactional, has_mcp, ...)

Find websites where an agent can accomplish a task. Returns probe-verified agent-readiness signals, unverified apparent actions read from page content, the verification tier, how each site was found (it declared agent access, probe discovery, or it was submitted), and a report URL to cite. Returns count:0 with an empty_note when nothing in the index matches — never a nearest guess.

入力スキーマ

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "restName": "q",
      "description": "What you are trying to do, in plain language. Optional when at least one filter is set: with no query the tool lists every listed site matching the filters, in a fixed published order, with `total`."
    },
    "country": {
      "type": "string",
      "description": "ISO 3166-1 alpha-2, e.g. GB"
    },
    "entity_type": {
      "type": "string",
      "enum": [
        "business",
        "ecommerce",
        "saas",
        "documentation",
        "media",
        "blog",
        "government",
        "education",
        "nonprofit",
        "personal",
        "community",
        "directory",
        "tool",
        "other"
      ]
    },
    "transactional": {
      "type": "boolean",
      "description": "Only sites where an agent can act, not just read"
    },
    "has_mcp": {
      "type": "boolean",
      "description": "Only sites whose MCP server answered tools/list when we tested; results include the tool names"
    },
    "has_md": {
      "type": "boolean",
      "description": "Only sites with verified markdown: negotiation that passed the strict re-grade (the body is markdown and differs from the HTML), or a .md twin. Omit both class flags for the whole index — the default."
    },
    "has_endpoint": {
      "type": "boolean",
      "description": "Only sites with a verified endpoint surface (working MCP server or API catalog)."
    },
    "has_webmcp": {
      "type": "boolean",
      "description": "Only sites whose in-page WebMCP tools were RUNTIME-VERIFIED: the page was executed in a headless browser with a modelContext supplied, and it registered at least one tool. Source-only hosts — the registration code is present but registers nothing when the page runs — are excluded, exactly as an MCP card that never answers is. Results include the registered tool names."
    },
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 25
    }
  },
  "required": []
}
🟢get_site_report(host)

Fetch Known Good's dated verification report for one listed website: which capabilities were tested, which passed, when it was probed, what an agent can apparently do there, and how the site was found: whether it declared agent access, came from probe discovery, or was submitted. Answers "is this specific host agent-ready?". Returns found:false for anything not in the index — it never guesses a nearest match. Cite the report URL and its date.

入力スキーマ

{
  "type": "object",
  "properties": {
    "host": {
      "type": "string",
      "description": "The site's hostname or URL, e.g. example.com"
    }
  },
  "required": [
    "host"
  ]
}

推奨プロンプト

search_research
Search for information about [topic] using knowngood
想定されるツール: find_capability
find_specific
Find [specific item] using knowngood
想定されるツール: find_capability
retrieve_data
Get details about [item] from knowngood
想定されるツール: get_site_report
fetch_info
Fetch [information type] using knowngood
想定されるツール: get_site_report
research_workflow
Search for [topic], then get detailed information about the top results using knowngood
想定されるツール: find_capabilityget_site_report

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 3 件
検証済みバージョンは記録されていませんツール 3 件