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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.