Server profile

MCP Shrimp Task Manager

Shrimp organizes AI-assisted development into planned, dependent tasks with persistent progress. It helps coding assistants retain project context, research decisions, and work through implementation and verification.

Server facts

MCP Shrimp Task Manager

Tech

Runtime / language
node
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
2,146
Last commit
Data as of

Tags

  • Ai Development
  • Persistent Memory
  • Project Planning
  • Task Management

Overview

MCP Shrimp Task Manager gives coding assistants a structured way to organize development work rather than treating each conversation as a fresh start. It preserves task progress between sessions and guides planning, execution, and verification. Requirements can be broken into smaller testable tasks, with dependencies and status updates keeping the sequence understandable. The intended audience is developers using MCP-compatible assistants such as Claude Code, Cline, or Claude Desktop.

Beyond task lists, Shrimp includes research workflows for comparing technologies and investigating solutions before implementation. Project rules provide a place to establish coding standards, while an agent system supports assigning specialized assistants to particular tasks. Task history can be backed up and restored. The README illustrates feature development, bug investigation, and framework evaluation as different entry points into the same planning process. These capabilities are described as guided workflows rather than a replacement for the connected coding client.

Installation involves cloning the repository, installing dependencies, and building the project before configuring a Node-based stdio process. A data directory is required for storage. Visual access is optional: a lightweight web GUI gives a quick overview, and a separate React task viewer adds drag-and-drop interaction, search, and multiple profiles. Teams wanting those interfaces should account for their additional setup rather than assuming they are part of the basic server launch.

Install & configure

Requirements

  • Node.js 18 or newer
  • npm or yarn
  • An MCP-compatible AI client
  • Repository dependencies installed and project built
Documented launch / install command
node /path/to/mcp-shrimp-task-manager/dist/index.js

Clone the repository, run npm install and npm run build, then replace the example script and storage paths. The README lists natural-language workflow commands but does not enumerate MCP tool identifiers.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Desktop configuration
{
  "mcpServers": {
    "mcp-shrimp-task-manager": {
      "command": "node",
      "args": [
        "/path/to/mcp-shrimp-task-manager/dist/index.js"
      ],
      "env": {
        "DATA_DIR": "<absolute directory for stored task data>",
        "TEMPLATES_USE": "<template language such as en>",
        "ENABLE_GUI": "<true to enable the optional GUI, otherwise false>"
      }
    }
  }
}

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "mcp-shrimp-task-manager": {
      "command": "node",
      "args": [
        "/path/to/mcp-shrimp-task-manager/dist/index.js"
      ],
      "env": {
        "DATA_DIR": "<absolute directory for stored task data>",
        "TEMPLATES_USE": "<template language such as en>",
        "ENABLE_GUI": "<true to enable the optional GUI, otherwise false>"
      }
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "mcp-shrimp-task-manager": {
      "type": "stdio",
      "command": "node",
      "args": [
        "/path/to/mcp-shrimp-task-manager/dist/index.js"
      ],
      "env": {
        "DATA_DIR": "<absolute directory for stored task data>",
        "TEMPLATES_USE": "<template language such as en>",
        "ENABLE_GUI": "<true to enable the optional GUI, otherwise false>"
      }
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "mcp-shrimp-task-manager": {
      "command": "node",
      "args": [
        "/path/to/mcp-shrimp-task-manager/dist/index.js"
      ],
      "env": {
        "DATA_DIR": "<absolute directory for stored task data>",
        "TEMPLATES_USE": "<template language such as en>",
        "ENABLE_GUI": "<true to enable the optional GUI, otherwise false>"
      }
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "mcp-shrimp-task-manager": {
      "type": "stdio",
      "command": "node",
      "args": [
        "/path/to/mcp-shrimp-task-manager/dist/index.js"
      ],
      "env": {
        "DATA_DIR": "<absolute directory for stored task data>",
        "TEMPLATES_USE": "<template language such as en>",
        "ENABLE_GUI": "<true to enable the optional GUI, otherwise false>"
      }
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

No individual tool names were confirmed in the source material. Check the repository for its current tool list.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Break a feature request into dependent implementation tasks.
  • Resume an assistant's work using stored task progress.
  • Research a technical choice before planning a migration.
  • Maintain project coding rules alongside task execution.

Strengths

  • Keeps task history across assistant sessions.
  • Combines planning, execution, research, and verification workflows.
  • Offers optional lightweight and React-based visual interfaces.

Limitations

  • Requires a source checkout and build in the documented setup.
  • The richer task viewer has its own installation steps.
  • Exact MCP tool identifiers are not stated in the README.

Frequently asked questions

Yes. The project describes persistent task progress and backup and restoration of task history.

No. Both the lightweight GUI and the separate task viewer are optional.

The README requires Node.js 18 or newer, with npm or yarn for installation.

Yes. Research mode explores technologies and solutions before those findings are turned into a task plan.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers