TaskWarrior MCP Server
MCP server that wraps TaskWarrior command-line tool. Provides 22 tools for task management, GTD workflow, and habit tracking.
README
TaskWarrior MCP Server
MCP server that wraps TaskWarrior command-line tool. Provides 22 tools for task management, GTD workflow, and habit tracking.
Tools
Basic Task Operations
add_task- Create task. Supports GTD fields (context, energy, scheduled, wait, depends) and recurring tasks (recur)modify_task- Update task attributesmark_task_done- Complete task by UUIDdelete_task- Delete task by UUIDlist_tasks- Query tasks with filters (status, project, tags, dates)get_task_details- Get single task by UUIDstart_task- Start timer on taskstop_task- Stop timer on taskadd_annotation- Add note to taskremove_annotation- Remove note from task
Dependencies
add_dependency- Make task A depend on task Bremove_dependency- Remove dependency link
GTD Workflow
get_next_actions- Filter actionable tasks by context, energy level, time availableprocess_inbox- Get tasks tagged +inbox for processingget_waiting_for- Get delegated/waiting tasks, grouped by blocker/date/projectget_blocked_tasks- Get tasks with unmet dependenciesget_project_status- Project metrics: next actions, completion %, stalenessweekly_review- GTD review data: inbox, completed, stalled projects, habitsget_someday_maybe- Get tasks tagged +someday
Batch Operations
create_project_tree- Create project with multiple tasks and dependencies in one callbatch_modify_tasks- Apply same modifications to multiple tasks
Habits/Recurring Tasks
get_recurring_tasks- Get recurring tasks with completion stats, streaks, frequency
Requirements
- Node.js 18+ for runtime
- Bun 1.3+ for development workflows
- TaskWarrior installed and available as
task
Install
bun install
bun run build
Run
bun run start
Or configure in your MCP client settings:
{
"mcpServers": {
"taskwarrior": {
"command": "node",
"args": ["/path/to/taskwarrior-mcp/dist/index.js"]
}
}
}
Claude Desktop Bundle
This repo now includes an MCPB manifest for Claude Desktop.
bun run mcpb:validate
bun run mcpb:pack
That produces dist/taskwarrior-mcp.mcpb.
The bundle packages the MCP server, but it does not bundle TaskWarrior itself. Users still need task installed on the host machine. For non-default setups, the MCPB manifest exposes optional TASK_BIN and TASKRC settings.
Response Format
All tools return MCP standard format:
{
"content": [
{
"type": "text",
"text": "{\"tasks\": [...], \"metadata\": {...}, \"insights\": {...}}"
}
]
}
GTD tools return enriched responses with:
tasks- Array of task objectsmetadata- Counts (total, actionable, blocked, waiting, completed)insights- Summary, recommendations, warningsgroups- Tasks grouped by project/context/frequencyrelationships- Dependency chains (where applicable)
GTD Features
Task Fields
scheduled- Date to start workwait- Hide until date (deferred)until- Task expires after datecontext- GTD context (@home, @work, @phone)energy- Energy level required (H/M/L)depends- Array of task UUIDs this depends onparent- Parent task UUIDrecur- Recurrence pattern (daily, weekly, monthly, etc.)
Recurring Tasks
Set recur with due to create habits:
{
"description": "Take vitamins",
"recur": "daily",
"due": "today",
"context": "@morning"
}
TaskWarrior creates template task (status:recurring) that generates instances. Use get_recurring_tasks to see completion rates and streaks.
Development
bun run typecheck # Type check source
bun run lint # Lint source
bun run test # Run integration tests against disposable Taskwarrior data
bun run build # Build dist/
bun run check # Run typecheck, lint, and tests
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。