mcp-taskmanager
Documentation
MCP TaskManager
Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.
Prerequisites
- Node.js 18+ (install via `brew install node`)
- Claude Desktop (install from https://claude.ai/desktop)
- tsx (install via `npm install -g tsx`)
Installation
1. Clone the Repository:
git clone https://github.com/pashpashpash/mcp-taskmanager.git
cd mcp-taskmanager2. Install Dependencies:
npm install3. Build the Project:
npm run build4. Configure Claude Desktop:
Locate your Claude Desktop configuration file at:
- macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
- Windows: `%APPDATA%/Claude/claude_desktop_config.json`
You can also find this through the Claude Desktop menu:
1. Open Claude Desktop
2. Click Claude on the Mac menu bar
3. Click "Settings"
4. Click "Developer"
Add the following to your configuration:
{
"tools": {
"taskmanager": {
"command": "node",
"args": ["path/to/mcp-taskmanager/dist/index.js"]
}
}
}Note: Replace "path/to/mcp-taskmanager" with the actual path to your cloned repository.
Development Setup
1. Install tsx globally (if not already installed):
npm install -g tsx2. Development Configuration:
For development with the TypeScript source, modify your Claude Desktop config:
{
"tools": {
"taskmanager": {
"command": "tsx",
"args": ["path/to/mcp-taskmanager/index.ts"]
}
}
}Available Operations
The TaskManager supports two main phases of operation:
Planning Phase
- Accepts a task list (array of strings) from the user
- Stores tasks internally as a queue
- Returns an execution plan (task overview, task ID, current queue status)
Execution Phase
- Returns the next task from the queue when requested
- Provides feedback mechanism for task completion
- Removes completed tasks from the queue
- Prepares the next task for execution
Parameters
- `action`: "plan" | "execute" | "complete"
- `tasks`: Array of task strings (required for "plan" action)
- `taskId`: Task identifier (required for "complete" action)
- `getNext`: Boolean flag to request next task (for "execute" action)
Example Usage
// Planning phase
{
action: "plan",
tasks: ["Task 1", "Task 2", "Task 3"]
}
// Execution phase
{
action: "execute",
getNext: true
}
// Complete task
{
action: "complete",
taskId: "task-123"
}Debugging
If you run into issues, check Claude Desktop's MCP logs:
tail -n 20 -f ~/Library/Logs/Claude/mcp*.logDevelopment
# Install dependencies
npm install
# Build the project
npm run build
# Development with auto-rebuild
npm run watchLicense
MIT
Note: This is a fork of the original mcp-taskmanager repository.
Frequently asked questions
What is mcp-taskmanager?
mcp-taskmanager is a Model Context Protocol (MCP) server listed in the TrackMCP directory.
How do I install mcp-taskmanager?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mcp-taskmanager open source?
Yes — it is hosted on GitHub at https://github.com/pashpashpash/mcp-taskmanager and has 32 stars.
Related MCP tools
A model context protocol server to work with JetBrains IDEs: IntelliJ, PyCharm, WebStorm, etc. Also, works with Android Studio
Web search using free google search (NO API KEYS REQUIRED)
A CLI inspector for the Model Context Protocol
An experiment in software planning using MCP
Adb-mcp is a proof of concept project to enabled AI control of Adobe tools (Adobe Photoshop and Adobe Premiere) by providing an interface to LLMs via the MCP...
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP