Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Yeti start a new strict-mode project for a mobile banking app"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Available on npm as yeti-mcp.
An MCP server that guides product design work through mandatory phases, so an AI assistant like Claude can run a project from problem to verified scope.
It covers five phases, in order:
discovery: problem, users and goal
definition: requirements (MoSCoW) and user stories
prioritization: RICE scoring of ideas
flows: Mermaid flow diagrams
verification: all must requirements completed, then the project closes
Projects have a mode, chosen at creation:
strict (default): a phase advances only when its requirements are met. advance_phase tells you what is missing.
free: phases advance regardless, and the response lists what was skipped.
Tool | What it does |
| Start a project in the discovery phase, in |
| Show phase, what is missing, and linked items |
| Move to the next phase, or list what is missing |
| Add a requirement with a MoSCoW priority |
| List requirements, filtered by priority, status or project |
| Export a project backlog as Markdown or CSV |
| Mark a requirement |
| Create a user story with acceptance criteria |
| Compute and sort RICE scores |
| Generate a Mermaid flow diagram, with Yes/No branches on decisions |
Requirements, stories, RICE scores and flows accept an optional projectId to link them to a project.
Related MCP server: Overseer MCP Server
Node.js 18 or later
git clone https://github.com/macorifice/yeti.git
cd yeti
npm install
npm run buildAdd this to claude_desktop_config.json, using the absolute path to dist/index.js on your machine:
{
"mcpServers": {
"yeti": {
"command": "node",
"args": ["/absolute/path/to/yeti/dist/index.js"]
}
}
}Restart Claude Desktop after editing the file.
Data is stored in data/db.json inside the project folder. To use another location, set the PRODUCT_DESIGN_DB environment variable:
"env": { "PRODUCT_DESIGN_DB": "/absolute/path/to/db.json" }npm testThe test starts the server on a temporary database and checks every tool and the phase flow.
Early version (0.2.0). Projects can run in strict or free mode.
MIT. See LICENSE.
This server cannot be deployed
Private projects, preflight, decisions, and handoffs that keep work continuous across AI tools.
Design, save, and run outcome-aligned AI workflows and verifiers, with reliable image output.
AI-native project management for tasks, docs, collaboration, and agents.
Helps your AI find the needle mover, then gives it the tools, people and files to get it done.
