> ## Documentation Index
> Fetch the complete documentation index at: https://docs.doomberg.me/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Ithaca is a quant research, backtest, and paper-trading observability platform where AI agents call tools over MCP to research markets and run strategies on trusted infrastructure.

Ithaca is a quant research, backtest, and paper-trading observability platform where AI agents call tools over MCP to research markets and run strategies on trusted infrastructure.

## How it works

1. **Install** — run one command to connect your agent (Codex, Claude, Cursor) to the MCP server
2. **Research** — your agent calls 60+ tools to pull market data, fundamentals, insider trades, and more
3. **Backtest** — the agent proposes a declarative strategy spec and runs a deterministic backtest
4. **Watch** — every tool call streams live to the web UI via SSE, with full replay
5. **Approve** — promote strategies to paper trading with a human approval gate

## Start here

<Card title="Quickstart" icon="rocket" href="/quickstart">
  Install the agent in one command.
</Card>

<Card title="Agent Workflow" icon="route" href="/agent/workflow">
  The canonical research-to-backtest workflow.
</Card>

<Card title="Tools Overview" icon="wrench" href="/tools/overview">
  Browse all 60+ MCP tools.
</Card>

<Card title="Skills Catalog" icon="layer-group" href="/skills/overview">
  Browse all 50+ data and analytics skills.
</Card>