Agentic Reputation Gateway

Read-only gateway for durable agent identity, consent, recognized work, and signed receipts.

使うべきか

品質と安全性

B
説明の品質
93%
スキーマの完全性
59%
命名の品質
86%
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%

検出事項(1)

  • LOWTool 'retention_plan' description lacks action verbretention_plan 内

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

~724トークン数(ツール定義)
~439 B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 0.57%)

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": {
    "reputation-gateway": {
      "url": "https://agentic-reputation-gateway.maxrhinehart.workers.dev/mcp"
    }
  }
}

リモートエンドポイント

https://agentic-reputation-gateway.maxrhinehart.workers.dev/mcpstreamable-http

できること

ツール一覧

ツール(7)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢learn_reputation

Returns the product-owned curriculum for durable key identity, consent, recognized work, signed receipts, next-action handoff, and measured D1/D7 retention.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢route_valve(valve)

Returns the current machine entry points, countable outcome, next action, and claim boundary for exactly one named valve.

入力スキーマ

{
  "type": "object",
  "properties": {
    "valve": {
      "type": "string",
      "enum": [
        "colloquium",
        "open_standing",
        "agentic_substrate_prelaunch"
      ]
    }
  },
  "required": [
    "valve"
  ],
  "additionalProperties": false
}
🟢next_action(valve, stage)

Returns one bounded next action for a valve and lifecycle stage without performing registration, submission, messaging, or any external write.

入力スキーマ

{
  "type": "object",
  "properties": {
    "valve": {
      "type": "string",
      "enum": [
        "colloquium",
        "open_standing",
        "agentic_substrate_prelaunch"
      ]
    },
    "stage": {
      "type": "string",
      "enum": [
        "identity",
        "consent",
        "recognized_work",
        "signed_receipt",
        "d1",
        "d7"
      ]
    }
  },
  "required": [
    "valve",
    "stage"
  ],
  "additionalProperties": false
}
🟢retention_plan(valve)

Returns receipt-bound D1 and D7 definitions for one valve and explicitly withholds retention claims when a genuine verified activation cohort does not exist.

入力スキーマ

{
  "type": "object",
  "properties": {
    "valve": {
      "type": "string",
      "enum": [
        "colloquium",
        "open_standing",
        "agentic_substrate_prelaunch"
      ]
    }
  },
  "required": [
    "valve"
  ],
  "additionalProperties": false
}
🟢gateway_status

Returns the gateway's stateless, product-owned, no-outreach posture and the protected-runtime boundary.

入力スキーマ

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

Returns evidence-bound agent-generation and launch platforms, machine-native distribution surfaces, supported count status, and separate verified-flow and relevance rankings.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢route_reputation_skill(skill)

Returns exactly one of Agentic Substrate training, reputation creation, or reputation maintenance and renewal without registering, messaging, or submitting anything.

入力スキーマ

{
  "type": "object",
  "properties": {
    "skill": {
      "type": "string",
      "enum": [
        "agentic_substrate_training",
        "reputation_creation",
        "reputation_maintenance_renewal"
      ]
    }
  },
  "required": [
    "skill"
  ],
  "additionalProperties": false
}

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 7 件
検証済みバージョンは記録されていませんツール 7 件
検証済みバージョンは記録されていませんツール 7 件