infinite-gratitude MCP — ユースケース, インストール & ライブデモ

なぜ使うのか

主な機能

10 agents with distinct roles
Structured handoffs between agents
Explicit critic role fights groupthink
Produces a synthesized final artifact
Multilingual (Chinese, Japanese, English in docs)

ライブデモ

実際の動作

infinite-gratitude-skill.replay ▶ 準備完了

0/0

インストール

クライアントを選択

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "infinite-gratitude-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/sstklen/infinite-gratitude",
        "~/.claude/skills/infinite-gratitude"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config を開く。保存後、アプリを再起動。

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "infinite-gratitude-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/sstklen/infinite-gratitude",
        "~/.claude/skills/infinite-gratitude"
      ],
      "_inferred": true
    }
  }
}

Cursor は Claude Desktop と同じ mcpServers スキーマを使用。プロジェクト設定はグローバルより優先。

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "infinite-gratitude-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/sstklen/infinite-gratitude",
        "~/.claude/skills/infinite-gratitude"
      ],
      "_inferred": true
    }
  }
}

Cline サイドバーの MCP Servers アイコンをクリックし、"Edit Configuration" を選択。

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "infinite-gratitude-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/sstklen/infinite-gratitude",
        "~/.claude/skills/infinite-gratitude"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop と同じ形式。Windsurf を再起動して反映。

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "infinite-gratitude-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/sstklen/infinite-gratitude",
        "~/.claude/skills/infinite-gratitude"
      ]
    }
  ]
}

Continue はマップではなくサーバーオブジェクトの配列を使用。

~/.config/zed/settings.json

{
  "context_servers": {
    "infinite-gratitude-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/sstklen/infinite-gratitude",
          "~/.claude/skills/infinite-gratitude"
        ]
      }
    }
  }
}

context_servers に追加。保存時に Zed がホットリロード。

claude mcp add infinite-gratitude-skill -- git clone https://github.com/sstklen/infinite-gratitude ~/.claude/skills/infinite-gratitude

ワンライナー。claude mcp list で確認、claude mcp remove で削除。

ユースケース

実用的な使い方： infinite-gratitude

Tackle a research question single-agent prompts fail on

👤 Researchers, analysts, strategists ⏱ ~60 min advanced

使うタイミング： Questions that need breadth (many sources) and depth (skepticism, synthesis) — where one pass hallucinates.

前提条件

Skill installed — git clone https://github.com/sstklen/infinite-gratitude ~/.claude/skills/infinite-gratitude

フロー

Pose the question

Use infinite-gratitude. Research question: what are the real bottlenecks in scaling post-transformer architectures in 2026? Run the 10-agent dojo.✓ コピーしました

→ Roles spin up: explorer, critic, synthesizer, etc., each producing a distinct contribution
Watch the handoffs

Show me the critic's pushback on the explorer's output.✓ コピーしました

→ Substantive critique, not agreement
Final synthesis

Give me the synthesizer's final artifact with dissent noted.✓ コピーしました

→ Document with main thesis + minority views preserved

結果： A research brief richer than a single-agent answer.

注意点

Agents converge and critic rubber-stamps — Prompt the critic explicitly to find flaws; force disagreement

組み合わせ： filesystem

Draft a policy memo with explicit dissenting views

👤 Policy wonks, internal strategy teams ⏱ ~90 min advanced

使うタイミング： The decision needs to survive scrutiny from people who'll disagree.

フロー

Frame the memo

Use infinite-gratitude. Memo topic: should our engineering org adopt four-day work weeks? Run the full dojo.✓ コピーしました

→ Multi-perspective outputs on pros, cons, empirical evidence, implementation risks
Extract the dissent

Keep the critic's dissent intact as an appendix; don't blend it away.✓ コピーしました

→ Main memo + appendix of unresolved concerns

結果： A memo your skeptics can see was genuinely considered.

組み合わせ

他のMCPと組み合わせて10倍の力を

infinite-gratitude-skill + paper-fetch-skill

Explorer agent downloads papers; synthesizer cites them

Run the dojo on [topic] and use paper-fetch-skill for the explorer's sources.✓ コピーしました

infinite-gratitude-skill + filesystem

Save each agent's output as its own file for traceability

Persist each agent's contribution to research/session-<date>/<role>.md✓ コピーしました

ツール

このMCPが提供する機能

ツール	入力	呼び出すタイミング	コスト
dojo_run	question, optional agent roster	Big, ambiguous questions	0 (but high token use)
single_agent	role name, task	Just one role needed	0

コストと制限

運用コスト

APIクォータ: None
呼び出しあたりのトークン: High — 10 agents each doing real work
金額: Free (Claude API usage applies)
ヒント: Use for high-stakes questions only. Single-agent suffices for most research.

セキュリティ

権限、シークレット、影響範囲

認証情報の保管： None

データ送信先： None from skill itself

トラブルシューティング

よくあるエラーと対処法

Dojo feels repetitive

Agents may be blending; enforce distinct perspectives in prompts

Runs out of context mid-session

Save intermediate outputs to disk and resume fresh; don't carry everything in one session

代替案

infinite-gratitude 他との比較

代替案	代わりに使う場面	トレードオフ
Single-agent with explicit steps	Straightforward questions	Less depth, cheaper
planning-with-files-skill	You want durable state across long sessions but not multi-role	No role specialization

その他

リソース

📖 GitHub の公式 README を読む

🐙 オープンな issue を見る

🔍 400以上のMCPサーバーとSkillsを見る