mcp-shrimp-task-manager MCP — Casos de uso, Instalar & Demo ao vivo

Por que usar

Principais recursos

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

Demo ao vivo

Como fica na prática

shrimp-task-manager.replay ▶ pronto

0/0

Instalar

Escolha seu cliente

~/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
    }
  }
}

Abra Claude Desktop → Settings → Developer → Edit Config. Reinicie após salvar.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor usa o mesmo esquema mcpServers que o Claude Desktop. Config de projeto vence a global.

VS Code → Cline → MCP Servers → Edit

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

Clique no ícone MCP Servers na barra lateral do Cline, depois "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Mesmo formato do Claude Desktop. Reinicie o Windsurf para aplicar.

~/.continue/config.json

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

O Continue usa um array de objetos de servidor em vez de um map.

~/.config/zed/settings.json

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

Adicione em context_servers. Zed recarrega automaticamente ao salvar.

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

Uma linha só. Verifique com claude mcp list. Remova com claude mcp remove.

Casos de uso

Usos do mundo real: mcp-shrimp-task-manager

Ship a multi-day feature across Claude sessions with Shrimp

👤 Solo devs on longer features ⏱ ~45 min intermediate

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

Pré-requisitos

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

Fluxo

Plan

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

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

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

→ One task finished, next queued
Resume tomorrow

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

→ Agent picks up where it left off

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

Armadilhas

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

Combine com: github

Research mode: explore options before committing code

👤 Engineers comparing approaches ⏱ ~30 min intermediate

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

Fluxo

Enter research mode

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

→ Research notes per option
Convert winner into tasks

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

→ Task graph aligned with decision

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

Combine com: idea-reality

Enforce project rules on every agent turn via Shrimp

👤 Teams with strict coding standards ⏱ ~15 min beginner

Quando usar: Agents keep forgetting your ESLint config or architecture constraints.

Fluxo

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.✓ Copiado

→ Rules saved
Execute with rules in-context

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

→ Agent respects rules without reminders

Resultado: Consistent output across a long session.

Combinações

Combine com outros MCPs para 10× de alavancagem

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.✓ Copiado

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.✓ Copiado

Ferramentas

O que este MCP expõe

Ferramenta	Entradas	Quando chamar	Custo
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

Custo e limites

O que custa rodar

Cota de API: Uses your LLM's quota
Tokens por chamada: Plan: 2-5k. Execute: depends on task
Monetário: Free
Dica: Avoid continuous_mode until you've validated a plan step-by-step for the current project

Segurança

Permissões, segredos, alcance

Armazenamento de credenciais: None intrinsic; wherever the executed tasks reach

Saída de dados: Task state stored locally in your configured data dir

Solução de problemas

Erros comuns e correções

Agent forgets task graph after restart

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

Verificar: 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

Alternativas

mcp-shrimp-task-manager vs. outros

Alternativa	Quando usar	Troca
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

Mais

Recursos

📖 Leia o README oficial no GitHub

🐙 Ver issues abertas

🔍 Ver todos os 400+ servidores MCP e Skills