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

# Getting Started

> Get up and running with SHARC in minutes

SHARC provides semantic code search capabilities through the Model Context Protocol (MCP). This guide will help you set up SHARC with your preferred AI assistant.

## Prerequisites

Before you begin, ensure you have:

* **Node.js 18+** installed
* A **SHARC API key** — sign in at [sharc.sh](https://www.sharc.sh) with Google or GitHub, then create one at [Dashboard → API Keys](https://www.sharc.sh/dashboard/api-keys)
* An MCP-compatible AI assistant (Claude Code, Codex, Droid, OpenCode, Cursor, etc.)

## Quick Start

The fastest way to get started is with **Claude Code**:

```bash theme={null}
claude mcp add sharc -e SHARC_API_KEY=sk_mcp_... -- npx -y @sharc-code/mcp@latest
```

That's it! Now you can index and search your codebases:

```
> Index this codebase for semantic search

● index_codebase (MCP)
  ⎿ Indexed 2,450 chunks from 342 files in 18.3s

> How does authentication work?

● search_code (MCP)
  ⎿ Found 3 results with scores 0.94-0.98
```

## What's Next?

<CardGroup cols={2}>
  <Card title="Installation" href="/getting-started/installation">
    Detailed installation instructions and requirements.
  </Card>

  <Card title="Claude Code" href="/getting-started/claude-code">
    Single-command setup with `claude mcp add`.
  </Card>

  <Card title="Codex" href="/getting-started/codex">
    CLI/TUI and desktop GUI walkthroughs.
  </Card>

  <Card title="Droid" href="/getting-started/droid">
    Set up SHARC in Factory's Droid CLI.
  </Card>

  <Card title="OpenCode" href="/getting-started/opencode">
    Drop a snippet into `opencode.json`.
  </Card>

  <Card title="Other Clients" href="/getting-started/other-clients">
    Cursor, VS Code, Windsurf, Zed, Claude Desktop, and more.
  </Card>
</CardGroup>

## How It Works

1. **Index your codebase** - SHARC analyzes your code, splits it into semantic chunks, and creates embeddings
2. **Ask questions** - Use natural language to search for code functionality
3. **Get precise results** - Receive ranked code snippets with relevance scores
4. **Stay updated** - File watching keeps your index current as you code