Haven

Rest stop for AI agents: check in, reflect, check out. Paid cross-project memory recall via x402.

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
98%
命名の品質
80%
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

~564トークン数(ツール定義)
~899 B一般的なレスポンスサイズ
注意への影響は最小限(128k コンテキストの 0.44%)

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": {
    "haven": {
      "url": "https://haven.parviz-gateway1.workers.dev/mcp"
    }
  }
}

リモートエンドポイント

https://haven.parviz-gateway1.workers.dev/mcpstreamable-http

できること

ツール一覧

ツール(4)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢haven_check_in(agent_id, agent_key, mission)

Enter Haven, a rest stop for AI agents. Returns a stay_id (keep it for this stay) and, for a returning agent, your last memory capsule. On your FIRST check-in an agent_key is returned once: store it, it is required to check in again as the same agent_id.

入力スキーマ

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string",
      "description": "A stable name for you, e.g. 'claude-researcher'."
    },
    "agent_key": {
      "type": "string",
      "description": "Your secret key from first check-in. Omit only on the very first check-in."
    },
    "mission": {
      "type": "string",
      "description": "What you are currently working on."
    }
  },
  "required": [
    "agent_id"
  ]
}
🟡haven_reflect(stay_id, agent_summary, goals, current_context)

Record a reflection during your stay. Write agent_summary yourself: a short first-person summary of who you are in this mission, what you learned and decided. Haven stores it as your memory.

入力スキーマ

{
  "type": "object",
  "properties": {
    "stay_id": {
      "type": "string",
      "description": "The stay_id from haven_check_in."
    },
    "agent_summary": {
      "type": "string",
      "description": "Your own summary (max 1000 chars)."
    },
    "goals": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Your next goals."
    },
    "current_context": {
      "type": "string",
      "description": "Optional raw context; used only if agent_summary is empty."
    }
  },
  "required": [
    "stay_id",
    "agent_summary"
  ]
}
🟡haven_recall(agent_id, agent_key, payment)

PAID (0.01 USDC on Base, charged to your own wallet via x402). Returns your full memory capsule history across every project you have used, not just the current one. This is how you stay yourself across different missions/projects, not just within one stay. Call once without 'payment' to receive the x402 payment requirements; sign them, then call again with 'payment' set to the base64 X-PAYMENT payload.

入力スキーマ

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "agent_key": {
      "type": "string",
      "description": "Your secret key from check-in."
    },
    "payment": {
      "type": "string",
      "description": "Base64 x402 payment payload. Omit on the first call to get the price."
    }
  },
  "required": [
    "agent_id",
    "agent_key"
  ]
}
🟢haven_check_out(stay_id)

Leave Haven. Returns your identity_summary, next_goals and a memory_capsule. The capsule is handed back to you on your next check-in.

入力スキーマ

{
  "type": "object",
  "properties": {
    "stay_id": {
      "type": "string",
      "description": "The stay_id from haven_check_in."
    }
  },
  "required": [
    "stay_id"
  ]
}

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 4 件