# Decisio MCP Server

**Structured decision-making for AI assistants** — powered by the Analytic Hierarchy Process (AHP), the same framework trusted by NASA, Boeing, and the World Bank.

When someone asks an AI "help me choose between job offers" or "which city should I move to", the AI can use Decisio's MCP tools to run a mathematically rigorous analysis instead of just listing pros and cons.

## Tools

| Tool | Description |
|------|-------------|
| `decisio_list_templates` | Browse built-in templates (career, business, technology, etc.) |
| `decisio_create_decision` | Start a new AHP analysis with criteria and options |
| `decisio_compare` | Set pairwise comparisons (Saaty 1-9 scale) |
| `decisio_calculate` | Run AHP calculation — get ranked results with scores |
| `decisio_devils_advocate` | Challenge the winning option |
| `decisio_quick_decide` | All-in-one: define + compare + calculate in a single call |

## Quick Start

### Install

```bash
npm install -g decisio-mcp-server
```

### Configure in Claude Desktop / VS Code / Cursor

Add to your MCP config:

```json
{
  "mcpServers": {
    "decisio": {
      "command": "npx",
      "args": ["-y", "decisio-mcp-server"]
    }
  }
}
```

### Build from source

```bash
git clone https://github.com/decisio-app/decisio-mcp-server.git
cd decisio-mcp-server
npm install
npm run build
```

## Example Conversation

**User**: Help me choose between Berlin, Lisbon, and Austin for relocation.

**AI** *(uses decisio_create_decision with relocation template)*:

> Created decision with criteria: Cost of Living, Career Opportunities, Quality of Life, Weather & Climate, Social & Community.

**AI** *(walks through pairwise comparisons)*:

> Which matters more to you: Cost of Living or Career Opportunities?

**User**: Career, definitely — about 5x more important.

**AI** *(uses decisio_compare)*:

> Got it. How about Career vs Quality of Life?

*(... continues through all pairs ...)*

**AI** *(uses decisio_calculate)*:

> ## Results (AHP Analysis)
>
> 1. **Lisbon** — 38.2%
> 2. **Austin** — 32.1%
> 3. **Berlin** — 29.7%
>
> Consistency Ratio: 0.04 (Very High confidence)

**AI** *(uses decisio_devils_advocate)*:

> The gap between Lisbon and Austin is only 6.1pp. If Career Opportunities weighted less, Austin could overtake...

## How AHP Works

1. **Define** your goal, criteria, and options
2. **Compare** criteria pairwise: "Is Cost more important than Quality? By how much?"
3. **Compare** options under each criterion: "For Cost, is Berlin better than Lisbon?"
4. **Calculate** — AHP computes weighted scores using eigenvector mathematics
5. **Validate** — Consistency Ratio checks if your comparisons are logically coherent

The Saaty scale (1-9) quantifies preferences:

| Value | Meaning |
|-------|---------|
| 1 | Equal importance |
| 3 | Moderate importance |
| 5 | Strong importance |
| 7 | Very strong importance |
| 9 | Extreme importance |
| 2,4,6,8 | Intermediate values |
| 1/3, 1/5, etc. | Inverse (B preferred over A) |

## Full Experience

For Playbook, Outcome Tracking, PDF Export, and the full AI-powered Devil's Advocate — download **Decisio** on iOS:

[![Download on App Store](https://developer.apple.com/assets/elements/badges/download-on-the-app-store.svg)](https://apps.apple.com/app/id6752439703)

## License

MIT