Shrimp Task Manager
MCP 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
What is Shrimp Task Manager?
Shrimp Task Manager is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp 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 trac...
MCP 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
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP Shrimp Task Manager is a task tool built for AI Agents,
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx shrimp-task-managerConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Shrimp Task Manager
MCP Shrimp Task Manager is a structured task management server built for AI coding agents that emphasizes chain-of-thought planning, reflection, and coding style consistency across long development sessions. It converts natural language feature requests into decomposed, dependency-tracked subtasks, assigns them to specialized agents, and maintains project rules to enforce consistent coding patterns throughout a codebase. Compatible with Claude Code, Cursor, RooCode, and other MCP clients, it bridges the gap between ad-hoc AI prompting and disciplined project execution by giving agents persistent, structured memory of what has been planned, started, and completed.
Prerequisites
- Node.js 18 or higher and npm or yarn
- An MCP-compatible AI client: Claude Code, Cursor, RooCode, or Windsurf
- Git (for cloning the repository if not using npx)
- Optional: A web browser to view the task viewer UI at http://localhost:5173
Clone and build the MCP Shrimp Task Manager
Clone the repository, install dependencies, and build the TypeScript project. The compiled output lands in the dist/ directory.
git clone https://github.com/cjo4m06/mcp-shrimp-task-manager.git
cd mcp-shrimp-task-manager
npm install
npm run buildCreate a data directory for task storage
Shrimp Task Manager persists tasks to disk in a directory you specify via the DATA_DIR environment variable. Create this directory before configuring the MCP server.
mkdir -p ~/shrimp_dataConfigure the MCP server in your AI client
Add the Shrimp Task Manager to your MCP client configuration file (.mcp.json for Claude Code, or the equivalent for your client). Set DATA_DIR to the path created above.
Initialize project rules for your codebase
Start a session with your AI agent and ask it to initialize project rules. This creates a coding standards document the agent will reference when breaking down future tasks.
Plan and execute a development task
Ask the agent to plan a task using natural language. It will decompose the request into subtasks with dependencies, then work through them one by one in continuous mode.
Launch the optional web-based task viewer
To monitor task progress in a visual interface, start the built-in task viewer web app. Set ENABLE_GUI=true in your config to activate the embedded link in responses.
cd tools/task-viewer
npm install
npm run start:all
open http://localhost:5173Shrimp Task Manager Examples
Client configuration
Add this block to your .mcp.json (Claude Code) or equivalent client config. Adjust the path to the built dist/index.js and set DATA_DIR to your preferred storage location.
{
"mcpServers": {
"shrimp-task-manager": {
"command": "node",
"args": ["/path/to/mcp-shrimp-task-manager/dist/index.js"],
"env": {
"DATA_DIR": "/Users/you/shrimp_data",
"TEMPLATES_USE": "en",
"ENABLE_GUI": "false"
}
}
}
}Prompts to try
Use these prompts to trigger Shrimp Task Manager's planning, execution, and reflection capabilities.
- "Plan task: add user authentication with JWT tokens and refresh token rotation."
- "Initialize project rules based on the existing code style in this repository."
- "Execute task in continuous mode until all subtasks are complete."
- "Show me all pending tasks and their dependencies."
- "Research the best approach for implementing rate limiting in our Express API, then plan the implementation."Troubleshooting Shrimp Task Manager
MCP server fails to start with 'Cannot find module dist/index.js'
The project must be built before use. Run `npm run build` inside the cloned repository directory. The compiled output goes to dist/index.js. Verify the path in your MCP config matches the actual location.
Tasks are not persisted between sessions
Check that DATA_DIR in your MCP server env config points to a writable directory that exists on disk. If the directory is missing or the path is wrong, the server silently falls back to in-memory storage and loses all tasks on restart.
Agent keeps re-planning the same tasks instead of making progress
Initialize project rules first with 'init project rules' so the agent has a stable context to work from. Also ensure TEMPLATES_USE is set to the correct language ('en' for English) so the chain-of-thought prompts are loaded correctly.
Frequently Asked Questions about Shrimp Task Manager
What is Shrimp Task Manager?
Shrimp Task Manager is a Model Context Protocol (MCP) server that mcp 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 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Shrimp Task Manager?
Follow the installation instructions on the Shrimp Task Manager GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Shrimp Task Manager?
Shrimp Task Manager works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Shrimp Task Manager free to use?
Yes, Shrimp Task Manager is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Shrimp Task Manager Alternatives — Similar Coding Agents Servers
Looking for alternatives to Shrimp Task Manager? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Shrimp Task Manager in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Shrimp Task Manager?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.