mcp-shrimp-task-manager MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

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

Live-Demo

In der Praxis

shrimp-task-manager.replay ▶ bereit

0/0

Installieren

Wählen Sie Ihren Client

~/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
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit

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

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json

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

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

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

In context_servers hinzufügen. Zed lädt beim Speichern neu.

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

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: mcp-shrimp-task-manager

Ship a multi-day feature across Claude sessions with Shrimp

👤 Solo devs on longer features ⏱ ~45 min intermediate

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

Voraussetzungen

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

Ablauf

Plan

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

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

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

→ One task finished, next queued
Resume tomorrow

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

→ Agent picks up where it left off

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

Fallstricke

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

Kombinieren mit: github

Research mode: explore options before committing code

👤 Engineers comparing approaches ⏱ ~30 min intermediate

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

Ablauf

Enter research mode

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

→ Research notes per option
Convert winner into tasks

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

→ Task graph aligned with decision

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

Kombinieren mit: idea-reality

Enforce project rules on every agent turn via Shrimp

👤 Teams with strict coding standards ⏱ ~15 min beginner

Wann einsetzen: Agents keep forgetting your ESLint config or architecture constraints.

Ablauf

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.✓ Kopiert

→ Rules saved
Execute with rules in-context

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

→ Agent respects rules without reminders

Ergebnis: Consistent output across a long session.

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

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.✓ Kopiert

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.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
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

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: Uses your LLM's quota
Tokens pro Aufruf: Plan: 2-5k. Execute: depends on task
Kosten in €: Free
Tipp: Avoid continuous_mode until you've validated a plan step-by-step for the current project

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: None intrinsic; wherever the executed tasks reach

Datenabfluss: Task state stored locally in your configured data dir

Fehlerbehebung

Häufige Fehler und Lösungen

Agent forgets task graph after restart

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

Prüfen: 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

Alternativen

mcp-shrimp-task-manager vs. andere

Alternative	Wann stattdessen	Kompromiss
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

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen