{"type":"mcp_server","name":"mcp-shrimp-task-manager","description":"AI Agent Task Manager. Converts natural language to structured dev tasks with dependency tracking and iterative refinement.","category":"AI","language":"TypeScript","stars":2134,"forks":141,"owner":"cjo4m06","github_url":"https://github.com/cjo4m06/mcp-shrimp-task-manager","homepage":"https://cjo4m06.github.io/mcp-shrimp-task-manager/","setup":"## Setup\n\n### Prerequisites\n\n*   **Node.js**: Ensure Node.js is installed on your system.\n*   **npm**: Node Package Manager, usually bundled with Node.js.\n\n### Installation\n\nThere are two primary methods for installing Shrimp Task Manager: via Smithery or manual installation.\n\n#### Installing via Smithery (Recommended for Claude Desktop)\n\nSmithery automates the installation process for Claude Desktop.\n\n```bash\nnpx -y @smithery/cli install @cjo4m06/mcp-shrimp-task-manager --client claude\n```\n\n#### Manual Installation\n\n1.  **Clone the repository (if necessary):**\n\n    If you haven't already, clone the Shrimp Task Manager repository to your local machine.\n2.  **Install dependencies:**\n\n    Navigate to the project directory in your terminal and run:\n\n    ```bash\n    npm install\n    ```\n\n3.  **Build the project:**\n\n    ```bash\n    npm run build\n    ```\n\n### Configuration\n\nShrimp Task Manager requires configuration to connect to an MCP-compatible client (e.g., Cursor IDE) and to set up data storage.\n\n#### Configuring with MCP-Compatible Clients (e.g., Cursor IDE)\n\nShrimp Task Manager supports global and project-specific configurations.  The recommended approach depends on whether your client supports the ListRoots protocol.\n\n**ListRoots Protocol Support (Recommended - e.g., Cursor IDE)**\n\nThe ListRoots protocol enables automatic project isolation and flexible path configuration.\n\n*   **Absolute Path Mode (Project Isolation):** Use a global `mcp.json` configuration. Shrimp automatically isolates projects by creating separate folders within the specified `DATA_DIR`.\n*   **Relative Path Mode (Project-Contained):** Create the `DATA_DIR` within your project root directory for project-specific data storage.\n\n**No ListRoots Protocol Support**\n\nIf your client doesn't support ListRoots, absolute paths for `DATA_DIR` are strongly recommended.\n\n**Configuration Steps:**\n\n1.  **Locate the MCP configuration file:**\n\n    *   **Global Configuration (e.g., Cursor IDE: `~/.cursor/mcp.json`):**  This configuration applies to all projects.\n    *   **Project-Specific Configuration:** Create a `.cursor` directory in the project root, and then create an `mcp.json` file inside it.\n\n2.  **Add the Shrimp Task Manager configuration:**\n\n    Add the following configuration to the `mcpServers` section of your `mcp.json` file. Choose either the Absolute Path or Relative Path option, as appropriate.\n\n    **Option A: Absolute Path (Project Isolation - Recommended with ListRoots)**\n\n    ```json\n    {\n      \"mcpServers\": {\n        \"shrimp-task-manager\": {\n          \"command\": \"node\",\n          \"args\": [\"/path/to/mcp-shrimp-task-manager/dist/index.js\"],\n          \"env\": {\n            \"DATA_DIR\": \"/Users/username/ShrimpData\", // Absolute path - creates project folders automatically\n            \"TEMPLATES_USE\": \"en\",\n            \"ENABLE_GUI\": \"false\"\n          }\n        }\n      }\n    }\n    ```\n\n    **Option B: NPX with Absolute Path (Project Isolation - Recommended with ListRoots)**\n\n    ```json\n    {\n      \"mcpServers\": {\n        \"shrimp-task-manager\": {\n          \"command\": \"npx\",\n          \"args\": [\"-y\", \"mcp-shrimp-task-manager\"],\n          \"env\": {\n            \"DATA_DIR\": \"/Users/username/ShrimpData\", // Absolute path - creates project folders automatically\n            \"TEMPLATES_USE\": \"en\",\n            \"ENABLE_GUI\": \"false\"\n          }\n        }\n      }\n    }\n    ```\n\n    **Option C: Relative Path (Project-Contained - Requires ListRoots for reliable operation)**\n\n    ```json\n    {\n      \"mcpServers\": {\n        \"shrimp-task-manager\": {\n          \"command\": \"node\",\n          \"args\": [\"/path/to/mcp-shrimp-task-manager/dist/index.js\"],\n          \"env\": {\n            \"DATA_DIR\": \".shrimp\", // Relative path - creates folder within project root\n            \"TEMPLATES_USE\": \"en\",\n            \"ENABLE_GUI\": \"false\"\n          }\n        }\n      }\n    }\n    ```\n\n    **Option D: NPX with Relative Path (Project-Contained - Requires ListRoots for reliable operation)**\n\n    ```json\n    {\n      \"mcpServers\": {\n        \"shrimp-task-manager\": {\n          \"command\": \"npx\",\n          \"args\": [\"-y\", \"mcp-shrimp-task-manager\"],\n          \"env\": {\n            \"DATA_DIR\": \"shrimp-data\", // Relative path - creates folder within project root\n            \"TEMPLATES_USE\": \"en\",\n            \"ENABLE_GUI\": \"false\"\n          }\n        }\n      }\n    }\n    ```\n\n    **Important Notes:**\n\n    *   Replace `/path/to/mcp-shrimp-task-manager` with the actual path to your Shrimp Task Manager installation.\n    *   Replace `/Users/username/ShrimpData` with your desired data directory.\n    *   If using NPX, ensure `mcp-shrimp-task-manager` is globally installed or available in your project's `node_modules`.\n    *   When using relative paths, the `DATA_DIR` will be created within your project directory (e.g., `./shrimp-data/`).\n    *   For clients that support ListRoots, absolute paths with project isolation are recommended for ease of use and project separation.\n\n### Environment Variables\n\nShrimp Task Manager uses environment variables for configuration. These can be set in your `mcp.json` file (as shown above) or in a `.env` file in the project root.\n\n*   **`DATA_DIR`**:  The directory where Shrimp Task Manager stores task data, conversation logs, and other information.  Use an absolute path for best results, especially if your client doesn't support ListRoots.\n*   **`TEMPLATES_USE`**: Specifies the template set to use for prompts. Defaults to `en` (English).  Other available option is `zh` (Traditional Chinese).  To use custom templates, copy the `src/prompts/templates_en` directory to the location specified by `DATA_DIR`, rename the copied directory (e.g., to `my_templates`), and set `TEMPLATES_USE` to the new directory name (e.g., `my_templates`).\n*   **`ENABLE_GUI`**: Enables or disables the web-based graphical user interface. Set to `true` to enable, `false` to disable (default).\n*   **`WEB_PORT`**: Specifies the port for the web GUI. If not specified, an available port will be automatically selected. Only takes effect when `ENABLE_GUI` is set to `true`.\n*   **`MCP_PROMPT_[FUNCTION_NAME]`**:  Overrides the default prompt for a specific function.  See the [Prompt Customization Guide](docs/en/prompt-customization.md) for details.\n*   **`MCP_PROMPT_[FUNCTION_NAME]_APPEND`**: Appends content to the existing prompt for a specific function. See the [Prompt Customization Guide](docs/en/prompt-customization.md) for details.\n\n**Example `.env` file:**\n\n```\nDATA_DIR=/Users/username/ShrimpData\nTEMPLATES_USE=en\nENABLE_GUI=true\nWEB_PORT=3000\n```\n\n### Running the Service\n\nAfter configuration, start the Shrimp Task Manager service. If using `node`, run:\n\n```bash\nnode dist/index.js\n```\n\nIf using NPX, the service will start automatically when you interact with it through your MCP-compatible client.\n\n### Using the Web GUI (Optional)\n\nIf you enabled the web GUI (`ENABLE_GUI=true`), a `WebGUI.md` file will be created in your `DATA_DIR` containing the access address.  Open this address in your web browser to access the GUI.","tools":"## Available Tools\n\nHere's a breakdown of the available tools and features within the MCP Shrimp Task Manager:\n\n**Features:**\n\n*   **Task Planning and Analysis:** Deep understanding and analysis of complex task requirements.\n*   **Intelligent Task Decomposition:** Automatically breaks down large tasks into manageable smaller tasks.\n*   **Dependency Management:** Precisely handles dependencies between tasks, ensuring correct execution order.\n*   **Execution Status Tracking:** Real-time monitoring of task execution progress and status.\n*   **Task Completeness Verification:** Ensures task results meet expected requirements.\n*   **Task Complexity Assessment:** Automatically evaluates task complexity and provides optimal handling suggestions.\n*   **Automatic Task Summary Updates:** Automatically generates summaries upon task completion, optimizing memory performance.\n*   **Task Memory Function:** Automatically backs up task history, providing long-term memory and reference capabilities.\n*   **Research Mode:** Systematic technical research capabilities with guided workflows for exploring technologies, best practices, and solution comparisons.  Example usage: \"Enter research mode for [your topic]\", \"Research [specific technology/problem]\".\n*   **Project Rules Initialization:** Defines project standards and rules to maintain consistency across large projects. Example usage: \"init rules\", \"update project rules\".\n*   **Web GUI:** Provides an optional web-based graphical user interface for task management. Enable by setting `ENABLE_GUI=true` in your `.env` file.\n\n**Tools:**\n\n| Category                     | Tool Name            | Description","faq":null,"created_at":"2025-04-12T08:59:07+00:00","updated_at":"2025-07-07T16:48:53+00:00","source_url":"https://model-context-protocol.com/servers/mcp-shrimp-task-manager","related_articles":[]}