Skip to main content

​
Prerequisites

Install uv if you don’t have it: 
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

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project):
{
  "mcpServers": {
    "nablr": {
      "command": "uvx",
      "args": ["nablr"]
    }
  }
}
Or via UI: Settings → MCP → Add New MCP Server
  • Name: nablr
  • Type: command
  • Command: uvx nablr
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.
One trial per device. If you see “trial already used for this device”, your 14-day window has expired. Subscribe at nablr.dev to continue.

​
Activate a paid key

After subscribing at 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: 
{
  "mcpServers": {
    "nablr": {
      "command": "uvx",
      "args": ["nablr"],
      "env": {
        "NABLR_API_KEY": "sk_nablr_<your-key-here>"
      }
    }
  }
}
NABLR_API_KEY always takes precedence over any locally stored key.

​
What you get per tier

FeatureFreeTrial / 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:
ProblemUse Case
Codebase full of unknown debtDebtRadar
AI-generated code shipping defectsShipSafe
Requirements no one can build fromSpecFirst
Production incident with unknown root causeForensicsIQ
Green CI but real failures in prodTestArchitect
Platform migration with no exit planMigrationPilot
AI-assisted dev with no audit trailGuardianCI
Schema change breaking unknown servicesContextMesh
Inherited codebase with no docsCode-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