mcp-shrimp-task-manager MCP — Cas d'usage, Installer & Démo en direct

Pourquoi l'utiliser

Fonctionnalités clés

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

Démo en direct

Aperçu en pratique

shrimp-task-manager.replay ▶ prêt

0/0

Installer

Choisissez votre 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
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

VS Code → Cline → MCP Servers → Edit

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

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json

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

Continue utilise un tableau d'objets serveur plutôt qu'une map.

~/.config/zed/settings.json

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

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

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

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : mcp-shrimp-task-manager

Ship a multi-day feature across Claude sessions with Shrimp

👤 Solo devs on longer features ⏱ ~45 min intermediate

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

Prérequis

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

Déroulement

Plan

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

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

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

→ One task finished, next queued
Resume tomorrow

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

→ Agent picks up where it left off

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

Pièges

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

Combiner avec : github

Research mode: explore options before committing code

👤 Engineers comparing approaches ⏱ ~30 min intermediate

Quand l'utiliser : You have 2-3 implementation options and want a structured exploration, not yolo.

Déroulement

Enter research mode

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

→ Research notes per option
Convert winner into tasks

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

→ Task graph aligned with decision

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

Combiner avec : idea-reality

Enforce project rules on every agent turn via Shrimp

👤 Teams with strict coding standards ⏱ ~15 min beginner

Quand l'utiliser : Agents keep forgetting your ESLint config or architecture constraints.

Déroulement

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.✓ Copié

→ Rules saved
Execute with rules in-context

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

→ Agent respects rules without reminders

Résultat : Consistent output across a long session.

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

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.✓ Copié

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.✓ Copié

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler	Coût
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

Coût et limites

Coût d'exécution

Quota d'API: Uses your LLM's quota
Tokens par appel: Plan: 2-5k. Execute: depends on task
Monétaire: Free
Astuce: Avoid continuous_mode until you've validated a plan step-by-step for the current project

Sécurité

Permissions, secrets, portée

Stockage des identifiants : None intrinsic; wherever the executed tasks reach

Sortie de données : Task state stored locally in your configured data dir

Dépannage

Erreurs courantes et correctifs

Agent forgets task graph after restart

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

Vérifier : 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

Alternatives

mcp-shrimp-task-manager vs autres

Alternative	Quand l'utiliser	Compromis
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

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills