TaskWarrior MCP Server
The TaskWarrior MCP Server is a Node.js server that enables interaction with TaskWarrior for task management via the Model Context Protocol (MCP). You can:
View pending tasks, with optional filtering by project or tags
Add new tasks with descriptions, due dates, priorities, projects, and tags
Mark tasks as complete by specifying their ID or UUID
Allows interaction with TaskWarrior, providing tools for viewing pending tasks, filtering tasks by project and tags, adding new tasks with descriptions and metadata, and marking tasks as complete.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@TaskWarrior MCP Server show me my high priority tasks for the work project"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
TaskWarrior MCP Server
Node.js server implementing Model Context Protocol (MCP) for TaskWarrior operations.
Features
View pending tasks
Filter tasks by project and tags
Add new tasks with descriptions, due dates, priorities, projects and tags
Mark tasks as complete
Note: This runs your local task binary, so TaskWarrior needs to be installed and configured!
This currently uses taskid which is an unstable identifier; taskwarrior
sometimes renumbers tasks when new ones are added or removed. In the future
this should be more careful, using task UUID instead.
Related MCP server: TickTick MCP Server
API
Tools
get_next_tasks
Get a list of all pending tasks
Optional filters:
project: Filter by project nametags: Filter by one or more tags
add_task
Add a new task to TaskWarrior
Required:
description: Task description text
Optional:
due: Due date (ISO timestamp)priority: Priority level ("H", "M", or "L")project: Project name (lowercase with dots)tags: Array of tags (lowercase)
mark_task_done
Mark a task as completed
Required:
identifier: Task ID or UUID
Usage with Claude Desktop
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"taskwarrior": {
"command": "npx",
"args": [
"-y",
"mcp-server-taskwarrior"
]
}
}
}Installation
npm install -g mcp-server-taskwarriorMake sure you have TaskWarrior (task) installed and configured on your system.
Example usage ideas:
What are my current work tasks?
Executes:
task project:work next
TODO: Call my sister (high priority)
Executes:
task add priority:H Call my sister
OK, I've called my sister
Executes:
task done 1
License
This MCP server is licensed under the MIT License. See the LICENSE file for details.
Available Tools
3 toolsadd_taskD
Add a new task
Inputs: description (required), due, priority, project, +1 more.
get_next_tasksC
Get a list of all pending tasks
Inputs: project, tags.
mark_task_doneC
Mark a task as done (completed)
Inputs: identifier (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: add_task creates new tasks, get_next_tasks retrieves pending tasks, and mark_task_done updates task status to completed. There is no overlap or ambiguity between these three core operations.
All tools follow a consistent verb_noun pattern (add_task, get_next_tasks, mark_task_done) with clear action verbs and descriptive nouns. The naming is predictable and readable throughout.
With only 3 tools, the server feels thin for task management. While the tools cover basic operations, typical task management systems benefit from more functionality like updating tasks, deleting tasks, or filtering/searching. The count is borderline minimal for the domain.
The tools provide basic CRUD coverage for tasks (create, read, update via marking done), but there are notable gaps. Missing operations include updating task details (beyond marking done), deleting tasks, and filtering/searching tasks beyond 'next' tasks. This limits agent flexibility in handling complex task workflows.
Maintenance
Related MCP Connectors
Model Context Protocol server for todo.vu task management and time tracking.
Official Todoist MCP server. Manage tasks and projects. Hosted, no API key needed.
Headless task management for bots, apps and AI agents. Remote MCP server, OAuth or access token.
Simple, fast todo app: manage tasks, projects and tags from Claude and other MCP clients.
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server that enables Large Language Models to interact with ClickUp workspace tasks and data, allowing creation and retrieval of tasks through natural language.19264 npm6MIT
- AlicenseAqualityDmaintenanceA Model Context Protocol server that integrates with TickTick task management service, allowing AI assistants to list, create, update, and complete tasks with proper timezone handling.95MIT
- AlicenseBqualityDmaintenanceA server implementation that enables LLMs to programmatically manage tasks in Todo.txt files using the Model Context Protocol (MCP), supporting operations like adding, completing, deleting, listing, searching, and filtering tasks.1111 npm9ISC
- AlicenseNot gradedqualityBmaintenanceA Model Context Protocol (MCP) server that brings your Google Tasks into Claude and other MCP-compatible clients, enabling task and task list management through natural conversation.73 npm13MIT