fizzy-mcp
MCP server for Fizzy (Kanban tool by 37signals) that enables AI assistants to read and manage boards, cards, columns, tags, comments, and more.
README
fizzy-mcp
MCP server for Fizzy — the Kanban tool by 37signals.
Lets AI assistants (Claude, etc.) read and manage your Fizzy boards, cards, columns, tags, comments and more.
Quick start
1. Get your Fizzy access token
Go to your Fizzy profile → Developer → Personal access tokens → Generate new access token with Read + Write permission.
Find your account slug — it's the number in your Fizzy URL: app.fizzy.do/<account_slug>/boards.
2. Configure
Claude Code
Add to your project's .mcp.json:
{
"mcpServers": {
"fizzy": {
"command": "uvx",
"args": ["fizzy-mcp"],
"env": {
"FIZZY_ACCESS_TOKEN": "your-token-here",
"FIZZY_ACCOUNT_SLUG": "your-slug-here"
}
}
}
}
Claude Desktop
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"fizzy": {
"command": "uvx",
"args": ["fizzy-mcp"],
"env": {
"FIZZY_ACCESS_TOKEN": "your-token-here",
"FIZZY_ACCOUNT_SLUG": "your-slug-here"
}
}
}
}
Available tools
Boards
| Tool | Description |
|---|---|
list_boards |
List all boards |
get_board |
Get a specific board |
create_board |
Create a new board |
update_board |
Update board name, access, auto-postpone |
delete_board |
Delete a board |
Columns
| Tool | Description |
|---|---|
list_columns |
List columns on a board |
create_column |
Create a column with name and color |
update_column |
Update column name or color |
delete_column |
Delete a column |
Cards
| Tool | Description |
|---|---|
list_cards |
List cards with filters (board, tags, assignees, status, dates, search) |
get_card |
Get a card by number |
create_card |
Create a card with title, description (HTML), tags |
update_card |
Update card title, description, tags |
delete_card |
Delete a card |
close_card |
Mark a card as done |
reopen_card |
Reopen a closed card |
triage_card |
Move a card into a column |
untriage_card |
Send a card back to triage |
postpone_card |
Move a card to Not Now |
mark_golden |
Star a card |
unmark_golden |
Unstar a card |
Tags
| Tool | Description |
|---|---|
list_tags |
List all tags |
toggle_tag |
Toggle a tag on/off for a card |
Assignments
| Tool | Description |
|---|---|
toggle_assignment |
Assign/unassign a user to a card |
self_assign |
Assign yourself to a card |
Comments
| Tool | Description |
|---|---|
list_comments |
List comments on a card |
get_comment |
Get a specific comment |
create_comment |
Add a comment (supports HTML) |
update_comment |
Edit a comment |
delete_comment |
Delete a comment |
Reactions
| Tool | Description |
|---|---|
list_reactions |
List reactions on a card |
add_reaction |
Add a reaction/boost (max 16 chars) |
remove_reaction |
Remove a reaction |
Steps (to-dos)
| Tool | Description |
|---|---|
create_step |
Add a to-do step to a card |
update_step |
Update step text or mark complete |
delete_step |
Delete a step |
Users
| Tool | Description |
|---|---|
list_users |
List active users |
get_user |
Get a specific user |
Notifications
| Tool | Description |
|---|---|
list_notifications |
List your notifications |
mark_notification_read |
Mark one as read |
mark_notification_unread |
Mark one as unread |
mark_all_notifications_read |
Mark all as read |
Pins & Watch
| Tool | Description |
|---|---|
list_pins |
List your pinned cards |
pin_card / unpin_card |
Pin or unpin a card |
watch_card / unwatch_card |
Subscribe/unsubscribe from card notifications |
Identity
| Tool | Description |
|---|---|
get_identity |
Get current user and accounts |
Development
git clone https://github.com/alexrbzz/fizzy-mcp.git
cd fizzy-mcp
pip install -e .
FIZZY_ACCESS_TOKEN=xxx FIZZY_ACCOUNT_SLUG=123 fizzy-mcp
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。