Monday.com Mcp 伺服器

MCP Server 是什麼？

MCP Server 是一個創新的工具，旨在促進與 Monday.com 板和項目的無縫互動。這個伺服器充當橋樑，允許用戶自動化工作流程、管理任務，並通過將 Monday.com 的各種功能整合到他們的應用程序中來提高生產力。使用 MCP Server，用戶可以輕鬆訪問和操作他們的 Monday.com 帳戶中的數據，使項目管理更加高效和流暢。

MCP Server 的特點

• 與 Monday.com 的整合：直接連接到 Monday.com，輕鬆管理板和項目。
• 自動化功能：自動化重複的任務和工作流程，以節省時間並減少手動工作。
• 友好的用戶界面：設計簡單易用，使用戶能夠輕鬆導航和利用其功能。
• 實時更新：獲取有關板和項目變更的即時通知和更新，確保您始終掌握最新情況。
• 可自定義的工作流程：根據您的特定項目管理需求調整伺服器的功能。

如何使用 MCP Server

1. 安裝：從 GitHub 的官方庫下載並安裝 MCP Server。
2. 配置：設置您的 Monday.com API 密鑰並配置伺服器設置以連接到您的 Monday.com 帳戶。
3. 創建板和項目：使用伺服器直接從您的應用程序創建新的板和項目。
4. 自動化任務：設置自動化規則，以根據您 Monday.com 工作區中的特定事件觸發操作。
5. 監控性能：利用伺服器的儀表板跟踪工作流程的性能並進行必要的調整。

常見問題

問：MCP Server 的主要目的是什么？

答：MCP Server 的主要目的是通過自動化任務和高效管理板和項目來增強與 Monday.com 的互動。

問：MCP Server 是免費使用的嗎？

答：是的，MCP Server 是開源的，並且在 GitHub 上免費提供。

問：我可以自定義伺服器以滿足我的需求嗎？

答：當然可以！MCP Server 設計為可自定義，允許您根據特定的項目管理需求調整其功能。

問：我該如何獲得 MCP Server 的支持？

答：您可以通過訪問 GitHub 倉庫獲得支持，在那裡您可以報告問題或在討論區提問。

問：MCP Server 周圍有社區嗎？

答：是的，有一個活躍的用戶和開發者社區，他們通過論壇和 GitHub 討論提供支持並為項目做出貢獻。

Monday.com MCP server

MCP Server for monday.com, enabling MCP clients to interact with Monday.com boards, items, updates, and documents.

Components

Tools

The server implements the following tools:

• monday-create-item: Creates a new item or sub-item in a Monday.com board
• monday-get-board-groups: Retrieves all groups from a specified Monday.com board
• monday-create-update: Creates a comment/update on a Monday.com item
• monday-list-boards: Lists all available Monday.com boards
• monday-list-items-in-groups: Lists all items in specified groups of a Monday.com board
• monday-list-subitems-in-items: Lists all sub-items for given Monday.com items
• monday-create-board: Creates a new Monday.com board
• monday-create-board-group: Creates a new group in a Monday.com board
• monday-move-item-to-group: Moves a Monday.com item to a different group
• monday-delete-item: Deletes a Monday.com item
• monday-archive-item: Archives a Monday.com item
• monday-get-item-updates: Retrieves updates/comments for a specific item
• monday-get-docs: Lists documents in Monday.com, optionally filtered by folder
• monday-get-doc-content: Retrieves the content of a specific document
• monday-create-doc: Creates a new document in Monday.com
• monday-add-doc-block: Adds a block to an existing document

Setup

1. Create and save a personal API Token in Monday.com by following the instructions here.
2. Get the Workspace Name from the URL of your Monday.com workspace. For example, if the URL is https://myworkspace.monday.com/, the workspace name is myworkspace.

Quickstart

Using Rube

1. Go to (Rube.app)[https://rube.app/]
2. Install Rube in your preferred client including Cursor, Claude, VS Code, Windsurf etc.,
3. Complete authentication with Rube
4. You can now execute actions on Monday.com like creating items, posting updates, moving items

Install

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json

On Windows: %APPDATA%/Claude/claude_desktop_config.json

Using uvx

"mcpServers": {
  "monday": {
    "command": "uvx",
    "args": [
      "mcp-server-monday"
    ],
    "env": {
      "MONDAY_API_KEY": "your-monday-api-key",
      "MONDAY_WORKSPACE_NAME": "your-monday-workspace-name"
    }
  }
}

Using Docker

"mcpServers": {
  "monday-docker": {
    "command": "docker",
    "args": [
      "run", 
      "--rm", 
      "-i", 
      "-e",
      "MONDAY_API_KEY=your-monday-api-key",
      "-e",
      "MONDAY_WORKSPACE_NAME=your-monday-workspace-name",
      "sakce/mcp-server-monday"
    ]
  }
}

Development

Building and Publishing

To prepare the package for distribution:

1. Sync dependencies and update lockfile:

uv sync

2. Build package distributions:

uv build

This will create source and wheel distributions in the dist/ directory.

3. Publish to PyPI:

uv publish

Note: You'll need to set PyPI credentials via environment variables or command flags:

• Token: --token or UV_PUBLISH_TOKEN
• Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector uv run mcp-server-monday

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.