ClickUp MCP Server
Enables AI assistants to interact directly with the ClickUp REST API v2 for managing tasks, folders, and lists. It supports full workspace hierarchy management, time tracking, and task operations through natural language.
README
ClickUp MCP Server
A robust Model Context Protocol (MCP) server for ClickUp. This server enables AI assistants (like OpenCode, Claude Desktop, etc.) to interact directly with your ClickUp workspace, allowing for natural language management of tasks, lists, folders, and more.
Unlike official adapters that may rely on limited proxies, this implementation connects directly to the ClickUp REST API v2, providing improved reliability and deep integration.
✨ Features
- Full Hierarchy Management: Create, update, and delete Spaces, Folders, and Lists.
- Task Operations: Create tasks, update status/details, fetch comments, and read custom fields.
- Tagging System: Manage tags (create/edit/delete) and apply them to tasks.
- Time Tracking: Start and stop timers, view time entries.
- Context Awareness: Inspect list schemas (statuses, custom fields) and user details.
- Search: (Limited) search for tasks within workspaces.
🚀 Quick Start
Prerequisites
- Node.js v18+
- A ClickUp Account
- A ClickUp OAuth App (Client ID & Secret). Create one here.
Installation
git clone https://github.com/yourusername/clickup-mcp.git
cd clickup-mcp
npm install
npm run build
Configuration & Authentication
-
Configure Credentials:
node dist/cli.js configure <YOUR_CLIENT_ID> <YOUR_CLIENT_SECRET> -
Login:
node dist/cli.js loginThis will open your browser to authenticate with ClickUp.
Integration with OpenCode
Run the registration script to add this server to your OpenCode configuration:
powershell -ExecutionPolicy Bypass -File scripts/register.ps1
Restart OpenCode, and the "ClickUp" tools will appear.
🛠️ Available Tools
The server exposes the following tools to the AI:
Task Management
get_tasks/get_task: Read tasks.create_task/update_task: Modify tasks.get_comments/create_comment: Collaborative features.
Hierarchy & Structure (CRUD)
- Workspaces (Teams):
get_workspaces - Spaces:
get_spaces,create_space,update_space,delete_space - Folders:
get_folders,create_folder,update_folder,delete_folder - Lists:
get_lists,create_list_in_folder,create_list_in_space,update_list,delete_list
Schema & Metadata
get_list_details: View list statuses, defaults, and configuration.get_accessible_custom_fields: View available custom fields for a list.get_current_user: Identify the authenticated user.
Tags
get_tags: List available tags.create_tag/edit_tag/delete_tag: Manage the tag library.add_tag_to_task/remove_tag_from_task: Apply tags.
Time Tracking
get_time_entries: View logs.start_timer/stop_timer: Control active sessions.
💻 Development
This project is built with TypeScript and Axios.
- Build:
npm run build - Test:
npm test(Runs comprehensive unit tests with 100% coverage) - Lint:
npm run lint
License
MIT
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。