mcp-shrimp-task-manager 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

Natural language → structured tasks with dependencies
Continuous mode runs tasks sequentially without re-prompting
Research mode for exploration before commit
Per-project rules enforced across agent turns

ライブデモ

実際の動作

shrimp-task-manager.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": {
    "shrimp-task-manager": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-shrimp-task-manager"
      ],
      "_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": {
    "shrimp-task-manager": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-shrimp-task-manager"
      ],
      "_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": {
    "shrimp-task-manager": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-shrimp-task-manager"
      ],
      "_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": {
    "shrimp-task-manager": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-shrimp-task-manager"
      ],
      "_inferred": true
    }
  }
}

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

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "shrimp-task-manager",
      "command": "npx",
      "args": [
        "-y",
        "mcp-shrimp-task-manager"
      ]
    }
  ]
}

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": {
    "shrimp-task-manager": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "mcp-shrimp-task-manager"
        ]
      }
    }
  }
}

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

claude mcp add shrimp-task-manager -- npx -y mcp-shrimp-task-manager

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： mcp-shrimp-task-manager

Ship a multi-day feature across Claude sessions with Shrimp

👤 Solo devs on longer features ⏱ ~45 min intermediate

使うタイミング： A feature is bigger than one Claude context window — you don't want to lose state.

前提条件

Repo cloned + built — npm install && npm run build in mcp-shrimp-task-manager; point .mcp.json at the data dir

フロー

Plan

Use Shrimp plan_task on 'implement two-factor auth'. Produce tasks with dependencies.✓ コピーしました

→ Task graph saved to disk
Execute one task at a time

execute_task next. When done, mark complete and show me the next.✓ コピーしました

→ One task finished, next queued
Resume tomorrow

(new session) Read Shrimp state and continue from the first open task.✓ コピーしました

→ Agent picks up where it left off

結果： Multi-session feature delivered without repeated context dumping.

注意点

Task graph drifts from reality after manual commits — Run a reconciliation step occasionally — diff completed tasks against actual repo state

組み合わせ： github

Research mode: explore options before committing code

👤 Engineers comparing approaches ⏱ ~30 min intermediate

使うタイミング： You have 2-3 implementation options and want a structured exploration, not yolo.

フロー

Enter research mode

Shrimp research_mode: compare three state management options for my React app — Zustand, Redux Toolkit, Jotai. Note tradeoffs.✓ コピーしました

→ Research notes per option
Convert winner into tasks

I'll go with Zustand. Convert the research conclusion into a task plan.✓ コピーしました

→ Task graph aligned with decision

結果： Informed decision tracked alongside the tasks to execute it.

組み合わせ： idea-reality

Enforce project rules on every agent turn via Shrimp

👤 Teams with strict coding standards ⏱ ~15 min beginner

使うタイミング： Agents keep forgetting your ESLint config or architecture constraints.

フロー

Set project rules

In Shrimp, set rules: (1) no any in TypeScript (2) all network code in the services/ layer (3) tests next to source.✓ コピーしました

→ Rules saved
Execute with rules in-context

Execute next task; Shrimp injects the rules automatically.✓ コピーしました

→ Agent respects rules without reminders

結果： Consistent output across a long session.

組み合わせ

他のMCPと組み合わせて10倍の力を

shrimp-task-manager + github

Each completed task becomes a commit with a linked PR

After each execute_task, commit with Conventional Commits format; when all tasks in the plan done, open a draft PR.✓ コピーしました

shrimp-task-manager + overture

Visual plan in Overture, persistent execution in Shrimp

Use Overture to approve the plan graph; then hand tasks to Shrimp for tracked execution.✓ 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
plan_task	description: str, rules?: str[]	Start of a feature	LLM tokens
execute_task	task_id?: str (defaults to next open)	Drive next step	LLM tokens + tool calls
research_mode	question: str	Pre-code exploration	LLM tokens
continuous_mode		When you trust the plan and want hands-off	can be high
set_rules	rules: str[]	Project onboarding	0

コストと制限

運用コスト

APIクォータ: Uses your LLM's quota
呼び出しあたりのトークン: Plan: 2-5k. Execute: depends on task
金額: Free
ヒント: Avoid continuous_mode until you've validated a plan step-by-step for the current project

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 intrinsic; wherever the executed tasks reach

データ送信先： Task state stored locally in your configured data dir

トラブルシューティング

よくあるエラーと対処法

Agent forgets task graph after restart

Ensure the data dir path in .mcp.json is stable and not /tmp

確認： cat the state file — tasks should be present

Continuous mode goes rogue

Kill the session; Shrimp keeps state so you can inspect and resume selectively

Build step fails on npm install

Requires Node 18+. Shrimp has native deps on some setups — check platform notes

代替案

mcp-shrimp-task-manager 他との比較

代替案	代わりに使う場面	トレードオフ
sequentialthinking-tools	You want in-session planning, not persistent tasks	No cross-session memory
Linear MCP	You want tasks in your team's issue tracker	Cloud/paid; team overhead

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