Shrimp Task Manager

Provides an intelligent MCP-driven task management workflow with memory, research mode, and project rules initialization.

typescript

1

GitHub Stars

typescript

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "samihalawa-gist-task-manager-mcp": {
      "command": "node",
      "args": [
        "/mcp-shrimp-task-manager/dist/index.js"
      ],
      "env": {
        "DATA_DIR": "YOUR_ABSOLUTE_PATH",
        "ENABLE_GUI": "false",
        "TEMPLATES_USE": "en"
      }
    }
  }
}

Shrimp Task Manager is an MCP-based system that guides AI Agents through structured workflows for efficient programming, robust task memory, and disciplined project rules. It helps you plan, decompose, and execute tasks while tracking progress, backing up task history, and enabling research-driven work across large codebases.

How to use

To work with the Shrimp Task Manager, you connect an MCP-compatible client and use guided prompts to plan, execute, and monitor tasks. Start by entering research mode or initializing project rules to tailor the environment to your project. Use the task planning flow to create a coherent plan, review it, and then execute the selected tasks. You can also enable continuous mode to run tasks in sequence without manual intervention.

How to install

Prerequisites: you need Node.js and npm installed on your system.

# Install via Smithery for Claude Desktop
npx -y @smithery/cli install @cjo4m06/mcp-shrimp-task-manager --client claude

# Manual installation
# Install dependencies
npm install

# Build and start service
npm run build

Available tools

plan_task

Start planning tasks based on user needs and project context to create a structured task set.

analyze_task

In-depth analysis of task requirements to refine scope and approach.

process_thought

Provide step-by-step reasoning for complex problems during planning.

reflect_task

Review and improve proposed solutions with feedback loops.

research_mode

Enter systematic technical research to explore technologies, patterns, and comparisons.

init_project_rules

Initialize or update project standards and rules to keep code quality and consistency.

split_tasks

Break down large tasks into smaller subtasks for better manageability.

list_tasks

Display all tasks with their current status.

query_task

Search for specific tasks and retrieve details.

get_task_detail

Show complete details for a selected task.

delete_task

Remove incomplete tasks from the queue.

execute_task

Execute a specific task by its ID or name.

verify_task

Verify that a task has been completed to the required standard.