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

# Quickstart

> Connect nablr to your AI assistant in under 2 minutes

## Prerequisites

Install `uv` if you don't have it:

```bash theme={null}
curl -LsSf https://astral.sh/uv/install.sh | sh
```

No other installation required — `uvx` fetches nablr on demand from PyPI.

## Connect to your AI assistant

<Tabs>
  <Tab title="Cursor">
    Add to `~/.cursor/mcp.json` (global) or `.cursor/mcp.json` (project):

    ```json theme={null}
    {
      "mcpServers": {
        "nablr": {
          "command": "uvx",
          "args": ["nablr"]
        }
      }
    }
    ```

    Or via UI: **Settings → MCP → Add New MCP Server**

    * Name: `nablr`
    * Type: `command`
    * Command: `uvx nablr`
  </Tab>

  <Tab title="Claude Desktop">
    Add to `claude_desktop_config.json`:

    * **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
    * **Windows**: `%APPDATA%\Claude\claude_desktop_config.json`

    ```json theme={null}
    {
      "mcpServers": {
        "nablr": {
          "command": "uvx",
          "args": ["nablr"]
        }
      }
    }
    ```
  </Tab>

  <Tab title="Windsurf">
    Add to `~/.codeium/windsurf/mcp_config.json`:

    ```json theme={null}
    {
      "mcpServers": {
        "nablr": {
          "command": "uvx",
          "args": ["nablr"]
        }
      }
    }
    ```
  </Tab>
</Tabs>

Restart your AI assistant after saving the config.

## Verify the connection

In your AI assistant, type:

```
What nablr agents are available?
```

You should see a list of agents with descriptions. No key required — nablr runs in free tier by default.

## Start a free trial

14-day full Pro access. No signup. No credit card. No browser required.

Tell your AI assistant:

```
Start my nablr trial
```

nablr generates a device ID, calls the license server, and stores a trial key at `~/.nablr_cache/trial_key.json`. Pro access activates immediately — no restart needed.

<Note>One trial per device. If you see "trial already used for this device", your 14-day window has expired. Subscribe at [nablr.dev](https://nablr.dev) to continue.</Note>

## Activate a paid key

After subscribing at [nablr.dev](https://nablr.dev), you receive a key by email (`sk_nablr_...`).

**Option 1 — via your AI assistant (recommended):**

```
Activate my key sk_nablr_<your-key-here>
```

**Option 2 — via environment variable (CI / team deployments):**

Add `env` to your MCP config:

<Tabs>
  <Tab title="Cursor">
    ```json theme={null}
    {
      "mcpServers": {
        "nablr": {
          "command": "uvx",
          "args": ["nablr"],
          "env": {
            "NABLR_API_KEY": "sk_nablr_<your-key-here>"
          }
        }
      }
    }
    ```
  </Tab>

  <Tab title="Claude Desktop">
    ```json theme={null}
    {
      "mcpServers": {
        "nablr": {
          "command": "uvx",
          "args": ["nablr"],
          "env": {
            "NABLR_API_KEY": "sk_nablr_<your-key-here>"
          }
        }
      }
    }
    ```
  </Tab>

  <Tab title="Windsurf">
    ```json theme={null}
    {
      "mcpServers": {
        "nablr": {
          "command": "uvx",
          "args": ["nablr"],
          "env": {
            "NABLR_API_KEY": "sk_nablr_<your-key-here>"
          }
        }
      }
    }
    ```
  </Tab>
</Tabs>

`NABLR_API_KEY` always takes precedence over any locally stored key.

## What you get per tier

| Feature                      | Free | Trial / Pro |
| ---------------------------- | ---- | ----------- |
| 40+ code scanners            | ✅    | ✅           |
| Workflow tools               | ✅    | ✅           |
| Codebase mapping (CODE\_MAP) | ✅    | ✅           |
| 19 SDLC persona prompts      | —    | ✅           |
| 34 rule files                | —    | ✅           |
| Language & framework configs | —    | ✅           |
| Offline asset cache          | —    | ✅           |

## Try a use case

Pick the problem that matches your situation:

| Problem                                     | Use Case                                      |
| ------------------------------------------- | --------------------------------------------- |
| Codebase full of unknown debt               | [DebtRadar](/use-cases/debt-radar)            |
| AI-generated code shipping defects          | [ShipSafe](/use-cases/ship-safe)              |
| Requirements no one can build from          | [SpecFirst](/use-cases/spec-first)            |
| Production incident with unknown root cause | [ForensicsIQ](/use-cases/forensics-iq)        |
| Green CI but real failures in prod          | [TestArchitect](/use-cases/test-architect)    |
| Platform migration with no exit plan        | [MigrationPilot](/use-cases/migration-pilot)  |
| AI-assisted dev with no audit trail         | [GuardianCI](/use-cases/guardian-ci)          |
| Schema change breaking unknown services     | [ContextMesh](/use-cases/context-mesh)        |
| Inherited codebase with no docs             | [Code-to-Clarity](/use-cases/code-to-clarity) |

## Full SDLC workflow

```
1. Set agent to discovery       → scan codebase, generate CODE_MAP
2. Set agent to product_manager → write requirements with testable AC
3. Set agent to qa_lead         → validate AC before development
4. Set agent to architect       → design boundaries and integration points
5. Set agent to developer       → implement with quality enforcement
6. Set agent to tester          → write real-execution tests
7. Set agent to pr_reviewer     → review for compliance + AI anti-patterns
```