mcp-shrimp-task-manager MCP — Use Cases, Install & Live Demo

Why use it

Key features

Natural language → structured tasks with dependencies
Continuous mode runs tasks sequentially without re-prompting
Research mode for exploration before commit
Per-project rules enforced across agent turns

Live Demo

What it looks like in practice

shrimp-task-manager.replay ▶ ready

0/0

Install

Pick your client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "shrimp-task-manager": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-shrimp-task-manager"
      ],
      "_inferred": true
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "shrimp-task-manager": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-shrimp-task-manager"
      ],
      "_inferred": true
    }
  }
}

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "shrimp-task-manager": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-shrimp-task-manager"
      ],
      "_inferred": true
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "shrimp-task-manager": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-shrimp-task-manager"
      ],
      "_inferred": true
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "shrimp-task-manager",
      "command": "npx",
      "args": [
        "-y",
        "mcp-shrimp-task-manager"
      ]
    }
  ]
}

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

{
  "context_servers": {
    "shrimp-task-manager": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "mcp-shrimp-task-manager"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add shrimp-task-manager -- npx -y mcp-shrimp-task-manager

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use mcp-shrimp-task-manager

Ship a multi-day feature across Claude sessions with Shrimp

👤 Solo devs on longer features ⏱ ~45 min intermediate

When to use: A feature is bigger than one Claude context window — you don't want to lose state.

Prerequisites

Repo cloned + built — npm install && npm run build in mcp-shrimp-task-manager; point .mcp.json at the data dir

Flow

Plan

Use Shrimp plan_task on 'implement two-factor auth'. Produce tasks with dependencies.✓ Copied

→ Task graph saved to disk
Execute one task at a time

execute_task next. When done, mark complete and show me the next.✓ Copied

→ One task finished, next queued
Resume tomorrow

(new session) Read Shrimp state and continue from the first open task.✓ Copied

→ Agent picks up where it left off

Outcome: Multi-session feature delivered without repeated context dumping.

Pitfalls

Task graph drifts from reality after manual commits — Run a reconciliation step occasionally — diff completed tasks against actual repo state

Combine with: github

Research mode: explore options before committing code

👤 Engineers comparing approaches ⏱ ~30 min intermediate

When to use: You have 2-3 implementation options and want a structured exploration, not yolo.

Flow

Enter research mode

Shrimp research_mode: compare three state management options for my React app — Zustand, Redux Toolkit, Jotai. Note tradeoffs.✓ Copied

→ Research notes per option
Convert winner into tasks

I'll go with Zustand. Convert the research conclusion into a task plan.✓ Copied

→ Task graph aligned with decision

Outcome: Informed decision tracked alongside the tasks to execute it.

Combine with: idea-reality

Enforce project rules on every agent turn via Shrimp

👤 Teams with strict coding standards ⏱ ~15 min beginner

When to use: Agents keep forgetting your ESLint config or architecture constraints.

Flow

Set project rules

In Shrimp, set rules: (1) no any in TypeScript (2) all network code in the services/ layer (3) tests next to source.✓ Copied

→ Rules saved
Execute with rules in-context

Execute next task; Shrimp injects the rules automatically.✓ Copied

→ Agent respects rules without reminders

Outcome: Consistent output across a long session.

Combinations

Pair with other MCPs for X10 leverage

shrimp-task-manager + github

Each completed task becomes a commit with a linked PR

After each execute_task, commit with Conventional Commits format; when all tasks in the plan done, open a draft PR.✓ Copied

shrimp-task-manager + overture

Visual plan in Overture, persistent execution in Shrimp

Use Overture to approve the plan graph; then hand tasks to Shrimp for tracked execution.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
plan_task	description: str, rules?: str[]	Start of a feature	LLM tokens
execute_task	task_id?: str (defaults to next open)	Drive next step	LLM tokens + tool calls
research_mode	question: str	Pre-code exploration	LLM tokens
continuous_mode		When you trust the plan and want hands-off	can be high
set_rules	rules: str[]	Project onboarding	0

Cost & Limits

What this costs to run

API quota: Uses your LLM's quota
Tokens per call: Plan: 2-5k. Execute: depends on task
Monetary: Free
Tip: Avoid continuous_mode until you've validated a plan step-by-step for the current project

Security

Permissions, secrets, blast radius

Credential storage: None intrinsic; wherever the executed tasks reach

Data egress: Task state stored locally in your configured data dir

Troubleshooting

Common errors and fixes

Agent forgets task graph after restart

Ensure the data dir path in .mcp.json is stable and not /tmp

Verify: cat the state file — tasks should be present

Continuous mode goes rogue

Kill the session; Shrimp keeps state so you can inspect and resume selectively

Build step fails on npm install

Requires Node 18+. Shrimp has native deps on some setups — check platform notes

Alternatives

mcp-shrimp-task-manager vs others

Alternative	When to use it instead	Tradeoff
sequentialthinking-tools	You want in-session planning, not persistent tasks	No cross-session memory
Linear MCP	You want tasks in your team's issue tracker	Cloud/paid; team overhead

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills