Kanban Zone MCP Server
Enables AI assistants to manage Kanban Zone workspaces via 23 tools for boards, cards, comments, checklists, and tasks.
README
Kanban Zone MCP Server
Model Context Protocol server that lets AI assistants (Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and any stdio-capable MCP client) drive your Kanban Zone workspace via the public API.
23 tools across boards, cards, comments, checklists, and tasks. No delete operations.
What you can do
- Read your boards, columns, labels, members, and custom fields.
- Create, list, get, update, and move cards.
- Inspect a card's history and time-in-column metrics.
- Add comments.
- Create, update, and list checklists — including bulk task creation in a single call.
- Create, update, and move tasks.
Quick start (Claude Desktop)
-
Get an API key. In Kanban Zone: Org Settings → Integrations → API Key. Copy the whole thing — it looks like
accessId:apiKey. -
Edit your config.
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{ "mcpServers": { "kanbanzone": { "command": "npx", "args": ["-y", "kanban-zone-mcp-server"], "env": { "KANBANZONE_API_KEY": "accessId:apiKey" } } } } - macOS:
-
Restart Claude Desktop. The Kanban Zone tools appear in the tool picker.
-
Try it. Ask Claude: "Is my Kanban Zone connection working?" — Claude calls
kanbanzone_get_meand replies with your org name.
Quick start (Claude Code)
claude mcp add kanbanzone \
-e KANBANZONE_API_KEY=accessId:apiKey \
-- npx -y kanban-zone-mcp-server
Configuration
| Variable | Required | Default | Description |
|---|---|---|---|
KANBANZONE_API_KEY |
yes | — | Composite credential accessId:apiKey. Generate in Org Settings → Integrations → API Key. |
KANBANZONE_BASE_URL |
no | https://integrations.kanbanzone.io/v1 |
Override only when pointing at a non-production environment. |
The server validates the key on startup. A missing or malformed value (no : separator) exits immediately with a message pointing at the org settings page.
Tools
23 tools, all prefixed with kanbanzone_:
| Group | Tools |
|---|---|
| Organization & Auth | get_me, get_organization |
| Boards | list_boards, get_board, list_board_columns, list_board_labels, list_board_members, list_board_custom_fields |
| Cards | create_card, list_cards, get_card, update_card, move_card, get_card_history, get_card_metrics |
| Comments | create_comment, list_card_comments |
| Checklists | create_checklist, update_checklist, list_card_checklists |
| Tasks | create_task, update_task, move_task |
User-facing docs with example prompts: https://docs.kanbanzone.io/mcp. Full input/output schemas: https://docs.kanbanzone.io/api.
Running from source
If you'd rather run from a local clone (development, contributions, custom modifications):
git clone https://github.com/kanbanzone/kanban-zone-mcp-server.git
cd kanban-zone-mcp-server
npm install
KANBANZONE_API_KEY=accessId:apiKey node src/index.js
Plain JavaScript — no compile step.
Troubleshooting
401 on every tool call. API key is wrong or expired. Regenerate it.
Tools don't appear in the client. Confirm the path is correct and the client was restarted after editing config. For npx installs, run npx -y kanban-zone-mcp-server once manually to make sure it downloads cleanly.
Card does not exist on a card you can see. It's a mirror — pass board=<publicId> to disambiguate which mirror.
Truncation warnings on list_cards. Paginate with page / count, or narrow with columns, owner, label, or daysSinceLastUpdate.
Security
This server runs locally on your machine. It does not transmit data to any third-party AI service — every API call goes directly to https://integrations.kanbanzone.io. Your API key never leaves your machine except as an Authorization: Basic header on those direct calls.
What's next
The server is local-stdio only today. A hosted version (paste a URL into your client, no install) is on the roadmap.
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。