mcp-shrimp-task-manager

Shrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavior in reasoning AI systems.

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio cjo4m06-mcp-shrimp-task-manager node /path/to/mcp-shrimp-task-manager/dist/index.js \
  --env DATA_DIR="/path/to/your/shrimp_data" \
  --env ENABLE_GUI="false" \
  --env TEMPLATES_USE="en"

How to use

Shrimp Task Manager is an MCP server that helps AI agents plan, decompose, and execute software development tasks with persistent context. It provides structured task management features such as intelligent planning, automatic task decomposition, dependency tracking, and progress monitoring, all while preserving memory across sessions. The server exposes tooling to initialize projects, plan tasks, execute tasks, and run in continuous mode, enabling a streamlined development workflow with AI agents that can handle both planning and execution steps. You can access a web-based task viewer and optional GUI interfaces to monitor progress and interact with task states as tasks are created and completed.

How to install

Prerequisites:

Node.js 18+
npm or yarn
Access to a compatible MCP client (e.g., Claude Code) to integrate with the MCP server

Installation steps:

Clone the repository: git clone https://github.com/cjo4m06/mcp-shrimp-task-manager.git cd mcp-shrimp-task-manager
Install dependencies: npm install
Build the project (if a build step is required by the project): npm run build
Run the server locally (example using the MCP config): Ensure you configure the mcp config to point to the built entry, then start your MCP client and load the config.
Optional: verify the server via the provided demos or the Task Viewer tooling in the repository documentation.

Additional notes

Environment variables:

DATA_DIR: path to where the server stores persistent task data.
TEMPLATES_USE: language/template set for task generation (e.g., en).
ENABLE_GUI: set to true to enable a web GUI if supported by your build. Common issues:
Ensure the dist/index.js path in the mcp_config matches your build output location.
If the server cannot access DATA_DIR, create the directory and grant appropriate permissions.
When using Claude Code or other clients, ensure the MCP configuration is loaded with the correct --mcp-config path. Security tip:
Do not expose the MCP server to untrusted networks without proper authentication and access controls.

Related MCP Servers

sonarqube

398

SonarQube MCP Server

skillz

370

An MCP server for loading skills (shim for non-claude clients).

agentql

149

Model Context Protocol server that integrates AgentQL's data extraction capabilities.

api2mcp4j

This is a revolutionary AI MCP plugin with excellent pluggable and encapsulated features. With just a few lines of configuration, it can easily integrate into your Spring boot web program and give it MCP capabilities,inheriting the powerful engineering capabilities of the Spring series framework

cursor10x

The Cursor10x MCP is a persistent multi-dimensional memory system for Cursor that enhances AI assistants with conversation context, project history, and code relationships across sessions.

mcp -js

MCP server that exposes YepCode processes as callable tools for AI platforms. Securely connect AI assistants to your YepCode workflows, APIs, and automations.