Introduction
Fizzy MCP is an open-source Model Context Protocol server that connects AI assistants to Fizzy, enabling intelligent, context-aware task management.
What is MCP?
The Model Context Protocol (MCP) is an open standard that allows AI assistants to interact with external tools and data sources. Instead of copy-pasting information between your AI and task manager, MCP lets them communicate directly.
What Can Fizzy MCP Do?
With Fizzy MCP, your AI assistant can:
- Read your boards and cards - Get full context about your projects
- Create new cards - Add tasks directly from conversation
- Update existing cards - Modify descriptions, tags, and status
- Move cards - Triage cards to columns, postpone, or close them
- Add comments - Leave notes and updates on cards
- Search and filter - Find specific cards by status, tags, or content
How It Works
┌──────────────────┐ ┌──────────────┐ ┌─────────────┐
│ AI Assistant │────▶│ Fizzy MCP │────▶│ Fizzy API │
│ (Claude, etc.) │◀────│ Server │◀────│ │
└──────────────────┘ └──────────────┘ └─────────────┘- Your AI sends requests through the MCP protocol
- Fizzy MCP translates them to Fizzy API calls
- Fizzy processes the request and returns results
- Your AI presents the information in conversation
Running the Server
Run the MCP server locally on your machine:
bash
npx fizzy-do-mcp@latestBenefits of local installation:
- Maximum privacy (tokens stay local)
- Best performance (no network hops)
- Full offline capability (once configured)
Requirements
- Node.js 18+ - For running the local MCP server
- Fizzy Account - Sign up at fizzy.do
- API Token - Generate from your Fizzy account settings
- MCP-Compatible Editor - Claude Desktop, Cursor, OpenCode, etc.