mcp-shrimp-task-manager MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

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

라이브 데모

실제 사용 모습

shrimp-task-manager.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/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 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

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

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

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

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

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

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

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

context_servers에 추가. 저장 시 Zed가 핫 리로드.

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

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: mcp-shrimp-task-manager

Ship a multi-day feature across Claude sessions with Shrimp

👤 Solo devs on longer features ⏱ ~45 min intermediate

언제 쓸까: A feature is bigger than one Claude context window — you don't want to lose state.

사전 조건

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

흐름

Plan

Use Shrimp plan_task on 'implement two-factor auth'. Produce tasks with dependencies.✓ 복사됨

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

execute_task next. When done, mark complete and show me the next.✓ 복사됨

→ One task finished, next queued
Resume tomorrow

(new session) Read Shrimp state and continue from the first open task.✓ 복사됨

→ Agent picks up where it left off

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

함정

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

함께 쓰기: github

Research mode: explore options before committing code

👤 Engineers comparing approaches ⏱ ~30 min intermediate

언제 쓸까: You have 2-3 implementation options and want a structured exploration, not yolo.

흐름

Enter research mode

Shrimp research_mode: compare three state management options for my React app — Zustand, Redux Toolkit, Jotai. Note tradeoffs.✓ 복사됨

→ Research notes per option
Convert winner into tasks

I'll go with Zustand. Convert the research conclusion into a task plan.✓ 복사됨

→ Task graph aligned with decision

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

함께 쓰기: idea-reality

Enforce project rules on every agent turn via Shrimp

👤 Teams with strict coding standards ⏱ ~15 min beginner

언제 쓸까: Agents keep forgetting your ESLint config or architecture constraints.

흐름

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.✓ 복사됨

→ Rules saved
Execute with rules in-context

Execute next task; Shrimp injects the rules automatically.✓ 복사됨

→ Agent respects rules without reminders

결과: Consistent output across a long session.

조합

다른 MCP와 조합해 10배 효율

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.✓ 복사됨

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.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
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

비용 및 제한

운영 비용

API 쿼터: Uses your LLM's quota
호출당 토큰: Plan: 2-5k. Execute: depends on task
금액: Free
팁: Avoid continuous_mode until you've validated a plan step-by-step for the current project

보안

권한, 시크릿, 파급범위

자격 증명 저장: None intrinsic; wherever the executed tasks reach

데이터 외부 송신: Task state stored locally in your configured data dir

문제 해결

자주 발생하는 오류와 해결

Agent forgets task graph after restart

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

확인: 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

대안

mcp-shrimp-task-manager 다른 것과 비교

대안	언제 쓰나	단점/장점
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

mcp-shrimp-task-manager