$git clone https://github.com/cjo4m06/mcp-shrimp-task-manager🇺🇸 English | 🇩🇪 Deutsch | 🇪🇸 Español | 🇫🇷 Français | 🇮🇹 Italiano | 🇮🇳 हिन्दी | 🇰🇷 한국어 | 🇧🇷 Português | [
| 1 | [🇺🇸 English](README.md) | [🇩🇪 Deutsch](docs/de/README.md) | [🇪🇸 Español](docs/es/README.md) | [🇫🇷 Français](docs/fr/README.md) | [🇮🇹 Italiano](docs/it/README.md) | [🇮🇳 हिन्दी](docs/hi/README.md) | [🇰🇷 한국어](docs/ko/README.md) | [🇧🇷 Português](docs/pt/README.md) | [🇷🇺 Русский](docs/ru/README.md) | [🇨🇳 中文](docs/zh/README.md) |
| 2 | |
| 3 | # MCP Shrimp Task Manager |
| 4 | |
| 5 | > 🦐 **Intelligent task management for AI-powered development** - Break down complex projects into manageable tasks, maintain context across sessions, and accelerate your development workflow. |
| 6 | |
| 7 | <div align="center"> |
| 8 | |
| 9 | [](https://www.youtube.com/watch?v=Arzu0lV09so) |
| 10 | |
| 11 | **[Watch Demo Video](https://www.youtube.com/watch?v=Arzu0lV09so)** • **[Quick Start](#-quick-start)** • **[Documentation](#-documentation)** |
| 12 | |
| 13 | [](https://smithery.ai/server/@cjo4m06/mcp-shrimp-task-manager) |
| 14 | <a href="https://glama.ai/mcp/servers/@cjo4m06/mcp-shrimp-task-manager"><img width="380" height="200" src="https://glama.ai/mcp/servers/@cjo4m06/mcp-shrimp-task-manager/badge" alt="Shrimp Task Manager MCP server" /></a> |
| 15 | |
| 16 | </div> |
| 17 | |
| 18 | ## 🚀 Quick Start |
| 19 | |
| 20 | ### Prerequisites |
| 21 | - Node.js 18+ |
| 22 | - npm or yarn |
| 23 | - MCP-compatible AI client (Claude Code, etc.) |
| 24 | |
| 25 | ### Installation |
| 26 | |
| 27 | #### Installing Claude Code |
| 28 | |
| 29 | **Windows 11 (with WSL2):** |
| 30 | ```bash |
| 31 | # First, ensure WSL2 is installed (in PowerShell as Administrator) |
| 32 | wsl --install |
| 33 | |
| 34 | # Enter Ubuntu/WSL environment |
| 35 | wsl -d Ubuntu |
| 36 | |
| 37 | # Install Claude Code globally |
| 38 | npm install -g @anthropic-ai/claude-code |
| 39 | |
| 40 | # Start Claude Code |
| 41 | claude |
| 42 | ``` |
| 43 | |
| 44 | **macOS/Linux:** |
| 45 | ```bash |
| 46 | # Install Claude Code globally |
| 47 | npm install -g @anthropic-ai/claude-code |
| 48 | |
| 49 | # Start Claude Code |
| 50 | claude |
| 51 | ``` |
| 52 | |
| 53 | #### Installing Shrimp Task Manager |
| 54 | |
| 55 | ```bash |
| 56 | # Clone the repository |
| 57 | git clone https://github.com/cjo4m06/mcp-shrimp-task-manager.git |
| 58 | cd mcp-shrimp-task-manager |
| 59 | |
| 60 | # Install dependencies |
| 61 | npm install |
| 62 | |
| 63 | # Build the project |
| 64 | npm run build |
| 65 | ``` |
| 66 | |
| 67 | ### Configure Claude Code |
| 68 | |
| 69 | Create a `.mcp.json` file in your project directory: |
| 70 | |
| 71 | ```json |
| 72 | { |
| 73 | "mcpServers": { |
| 74 | "shrimp-task-manager": { |
| 75 | "command": "node", |
| 76 | "args": ["/path/to/mcp-shrimp-task-manager/dist/index.js"], |
| 77 | "env": { |
| 78 | "DATA_DIR": "/path/to/your/shrimp_data", |
| 79 | "TEMPLATES_USE": "en", |
| 80 | "ENABLE_GUI": "false" |
| 81 | } |
| 82 | } |
| 83 | } |
| 84 | } |
| 85 | ``` |
| 86 | |
| 87 | Example configuration: |
| 88 | ```json |
| 89 | { |
| 90 | "mcpServers": { |
| 91 | "shrimp-task-manager": { |
| 92 | "command": "node", |
| 93 | "args": ["/home/fire/claude/mcp-shrimp-task-manager/dist/index.js"], |
| 94 | "env": { |
| 95 | "DATA_DIR": "/home/fire/claude/project/shrimp_data", |
| 96 | "TEMPLATES_USE": "en", |
| 97 | "ENABLE_GUI": "false" |
| 98 | } |
| 99 | } |
| 100 | } |
| 101 | } |
| 102 | ``` |
| 103 | |
| 104 | Then start Claude Code with your custom MCP configuration: |
| 105 | |
| 106 | ```bash |
| 107 | claude --dangerously-skip-permissions --mcp-config .mcp.json |
| 108 | ``` |
| 109 | |
| 110 | <details> |
| 111 | <summary><b>Other AI Clients</b></summary> |
| 112 | |
| 113 | **Cline (VS Code Extension)**: A VS Code extension for AI-assisted coding. Add to VS Code settings.json under `cline.mcpServers` |
| 114 | |
| 115 | **Claude Desktop**: Add to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\Claude\claude_desktop_config.json` (Windows) |
| 116 | </details> |
| 117 | |
| 118 | ### Start Using |
| 119 | |
| 120 | 1. **Initialize your project**: `"init project rules"` |
| 121 | 2. **Plan a task**: `"plan task: implement user authentication"` |
| 122 | 3. **Execute tasks**: `"execute task"` or `"continuous mode"` |
| 123 | |
| 124 | ## 💡 What is Shrimp? |
| 125 | |
| 126 | Shrimp Task Manager is an MCP (Model Context Protocol) server that transforms how AI agents approach software development. Instead of losing context or repeating work, Shrimp provides: |
| 127 | |
| 128 | - **🧠 Persistent Memory**: Tasks and progress persist across sessions |
| 129 | - **📋 Structured Workflows**: Guided processes for planning, execution, and verification |
| 130 | - **🔄 Smart Decomposition**: Automatically breaks complex tasks into manageable subtasks |
| 131 | - **🎯 Context Preservation**: Never lose your place, even with token limits |
| 132 | |
| 133 | ## ✨ Core Features |
| 134 | |
| 135 | ### Task Management |
| 136 | - **Intelligent Plannin |