An MCP (Model Context Protocol) server that helps AI assistants (like Claude) break down complex tasks into manageable steps, track progress, and manage a hierarchical task list.
# Clone the repository
git clone https://github.com/yourusername/task-planner-mcp.git
cd task-planner-mcp
# Install dependencies
pnpm install
# Build the project
pnpm run build
pnpm start
To use this MCP server with Claude Desktop, add the following to your claude_desktop_config.json
file:
{
"mcpServers": {
"task-planner": {
"command": "node",
"args": ["/absolute/path/to/task-planner-mcp/dist/index.js"]
}
}
}
Replace /absolute/path/to/task-planner-mcp
with the absolute path to your task planner directory.
The Task Planner MCP Server provides the following tools:
create-task
Create a new task or subtask.
Parameters:
title
: Title of the taskdescription
(optional): Detailed description of the taskparentId
(optional): ID of the parent task if this is a subtaskpriority
(optional): Priority level of the task (low, medium, high)list-tasks
List all tasks or subtasks.
Parameters:
parentId
(optional): ID of the parent task to list subtasks forget-task
Get detailed information about a task.
Parameters:
id
: ID of the task to retrievecomplete-task
Mark a task as completed.
Parameters:
id
: ID of the task to completeupdate-task
Update a task's details.
Parameters:
id
: ID of the task to updatetitle
(optional): New title for the taskdescription
(optional): New description for the taskpriority
(optional): New priority level for the task (low, medium, high)delete-task
Delete a task and its subtasks.
Parameters:
id
: ID of the task to deletebreak-down-task
Break down a complex task into multiple subtasks.
Parameters:
parentId
: ID of the parent task to break downsubtasks
: Array of subtask objects, each with:
title
: Title of the subtaskdescription
(optional): Description of the subtaskpriority
(optional): Priority of the subtask (low, medium, high)Here are some examples of how to use the Task Planner with Claude:
Task data is stored in a local JSON file (tasks.json
) in the root directory of the project.
ISC
{
"mcpServers": {
"task-planner": {
"env": {},
"args": [
"/absolute/path/to/task-planner-mcp/dist/index.js"
],
"command": "node"
}
}
}
Seamless access to top MCP servers powering the future of AI integration.