Fizzy Do MCP
Open-source MCP server that connects AI assistants to Fizzy (Basecamp's task management) with 70+ tools for boards, cards, workflows, and AI-powered project management.
README
Fizzy Do MCP
Open-source MCP server that connects AI assistants to Fizzy (Basecamp's task management) with 70+ tools for boards, cards, workflows, and AI-powered project management.
What It Is
Fizzy Do MCP is a Model Context Protocol server that gives AI assistants full read/write access to Fizzy. Rather than switching between your editor and a project management UI, you manage boards, cards, comments, tags, and workflows through conversation. The tool surface covers the complete Fizzy API: card lifecycle (create, update, close, reopen, triage, postpone), board management, column workflows, checklist steps, reactions, notifications, and webhooks.
It also includes AI-powered project management tools — standup generation, progress tracking, and session management — that synthesize project state from card data rather than requiring manual status updates.
Quick Start
npx fizzy-do-mcp configure
The interactive wizard detects installed editors and configures them automatically.
Manual configuration:
{
"mcpServers": {
"fizzy": {
"command": "npx",
"args": ["-y", "fizzy-do-mcp"],
"env": {
"FIZZY_TOKEN": "your-fizzy-api-token"
}
}
}
}
Supported Editors
| Editor | Status | Guide |
|---|---|---|
| Claude Desktop | Full support | Configure |
| Claude Code | Full support | Configure |
| Cursor | Full support | Configure |
| Windsurf | Full support | Configure |
| Continue | Full support | Configure |
| OpenCode | Full support | Configure |
Available Tools
70+ tools across these categories:
| Category | Description |
|---|---|
| Boards | List, create, update, delete, publish/unpublish |
| Cards | Full lifecycle — create, update, close, reopen, triage, postpone |
| Comments | Add, edit, delete on cards |
| Columns | Manage workflow stages |
| Tags & Users | List, lookup, assign |
| Reactions | Emoji reactions on cards and comments |
| Steps | Checklist items within cards |
| Notifications | Read and manage |
| Webhooks | Configure integrations |
| Project Manager | AI standups, progress tracking, sessions |
Architecture
fizzy-do-mcp/
├── packages/
│ ├── @fizzy-do-mcp/shared/ # Types, schemas, Result type
│ ├── @fizzy-do-mcp/client/ # Type-safe Fizzy API client
│ └── @fizzy-do-mcp/tools/ # MCP tool definitions
├── apps/
│ └── server/ # CLI and MCP server
└── docs/ # Documentation (VitePress)
Why This Matters
MCP servers tend to be thin wrappers around a single API. Fizzy Do MCP is more opinionated: the project management tools (standups, progress tracking) demonstrate that MCP tools can synthesize across multiple API calls rather than just proxying them. The AI doesn't just read your board — it generates a standup from card state across all your boards.
Status
Published on npm. Active development. Full documentation at fizzy.yogan.dev.
Stack
- Runtime: Node.js 20+
- Language: TypeScript
- Protocol: Model Context Protocol (MCP)
- Build: Vite+ (vp), Changesets for versioning
- Docs: VitePress
CLI
npx fizzy-do-mcp configure # Interactive setup wizard
npx fizzy-do-mcp whoami # Check current identity
npx fizzy-do-mcp status # View configuration status
npx fizzy-do-mcp logout # Clear stored credentials
npx fizzy-do-mcp # Run as MCP server
License
MIT — Ryan Yogan
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。