Worksection MCP Server
Enables AI assistants to interact with the Worksection project management platform to manage projects, tasks, comments, and members through natural language. It provides a comprehensive suite of tools for task execution and project oversight while automatically handling API rate limits.
README
worksection-mcp-server
MCP (Model Context Protocol) server for Worksection — a project management platform popular in Ukraine and Eastern Europe.
This server enables AI assistants like Claude to interact with your Worksection account: manage projects, tasks, comments, members, and tags through natural language.
Features
Projects
worksection_get_projects— List all projects with optional status filterworksection_get_project— Get detailed project infoworksection_create_project— Create a new projectworksection_update_project— Update project detailsworksection_archive_project— Archive a projectworksection_activate_project— Activate an archived projectworksection_get_project_folders— List project folders
Tasks
worksection_get_all_tasks— List all tasks across projectsworksection_get_tasks— List tasks in a specific projectworksection_get_task— Get detailed task infoworksection_create_task— Create a task (or subtask)worksection_update_task— Update task detailsworksection_complete_task— Mark task as doneworksection_reopen_task— Reopen a completed taskworksection_search_tasks— Search tasks by text, assignee, dates, etc.
Comments
worksection_get_comments— Get all comments on a taskworksection_post_comment— Post a comment to a task
Members
worksection_get_members— List all account membersworksection_add_project_members— Add members to a project
Tags
worksection_get_tags— List available tags/labelsworksection_set_task_tags— Set tags on a task
Prerequisites
- Node.js 18+
- A Worksection account with admin access (for the API key)
Setup
1. Get your API key
Go to Account → API → Show API key in your Worksection account.
Only the account owner has access to the admin API key.
2. Install
git clone https://github.com/YOUR_USERNAME/worksection-mcp-server.git
cd worksection-mcp-server
npm install
npm run build
3. Configure
Set environment variables:
export WORKSECTION_URL=https://yourcompany.worksection.com
export WORKSECTION_API_KEY=your_api_key_here
Or create a .env file (see .env.example).
Usage
With Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"worksection": {
"command": "node",
"args": ["/path/to/worksection-mcp-server/dist/index.js"],
"env": {
"WORKSECTION_URL": "https://yourcompany.worksection.com",
"WORKSECTION_API_KEY": "your_api_key_here"
}
}
}
}
With Claude Code
claude mcp add worksection -- node /path/to/worksection-mcp-server/dist/index.js
Make sure WORKSECTION_URL and WORKSECTION_API_KEY are set in your shell environment.
Direct execution
WORKSECTION_URL=https://yourcompany.worksection.com \
WORKSECTION_API_KEY=your_key \
node dist/index.js
API Rate Limits
Worksection enforces a 1 request per second rate limit. This MCP server automatically handles rate limiting — requests are queued with a minimum 1.1s interval.
Authentication
This server uses the Admin Token authentication method:
- Generates MD5 hash from query parameters + API key
- Provides full access to all account data
- Only the account owner can generate the API key
For OAuth 2.0 support (per-user access), see the Worksection OAuth docs.
Security
- API key is read from environment variables only, never hardcoded
- All inputs are validated with Zod schemas
- The server runs locally via stdio transport — no network exposure
- Worksection API does not allow deletion of projects, tasks, comments, or members via API (safety by design)
Development
npm run dev # Watch mode (auto-recompile)
npm run build # One-time build
npm start # Run the server
Project Structure
worksection-mcp-server/
├── src/
│ ├── index.ts # Server entry point
│ ├── types.ts # TypeScript type definitions
│ ├── constants.ts # Shared constants
│ ├── services/
│ │ ├── client.ts # Worksection API client (auth + rate limit)
│ │ └── formatters.ts # Markdown formatting helpers
│ └── tools/
│ ├── projects.ts # Project management tools
│ ├── tasks.ts # Task management tools
│ ├── comments.ts # Comment tools
│ ├── members.ts # Member/team tools
│ └── tags.ts # Tag/label tools
├── package.json
├── tsconfig.json
└── README.md
License
MIT #� �w�o�r�k�s�e�c�t�i�o�n�-�m�c�p�-�s�e�r�v�e�r� � �
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。