nablr

Security Scan Python 3.12+ PyPI

AI-powered SDLC governance via Model Context Protocol.

nablr (pronounced like "enabler") connects to your AI assistant (Cursor, Claude Desktop, Windsurf) and enforces quality gates across your entire software delivery lifecycle — 18 expert personas, 12 built-in scanners, full workflow orchestration.

Documentation: docs.nablr.dev

Why nablr

AI assistants accelerate typing, not engineering.

What they promised	What actually happens
Ship faster	More code, same bugs
Higher quality	AI-generated tech debt
Reduce costs	Increased rework cycles

nablr is the orchestration layer that fixes this: quality enforcement, workflow context, and persistent state injected directly into your AI assistant via MCP.

Free vs paid

Capability	Free	Pro
12 built-in scanners	✅	✅
Workflow orchestration	✅	✅
Codebase mapping	✅	✅
Persona prompts	2 (`discovery`, `platform_engineer`)	18 (all)
Rule files + language/framework configs	Ships in every install, read from disk	Ships in every install, plus server-fetched freshness
14-day trial (full Pro)	✅	—

Installation

Requires uv.

Add to your AI assistant config:

{
  "mcpServers": {
    "nablr": {
      "command": "uvx",
      "args": ["nablr"]
    }
  }
}

Config file locations:

Cursor: ~/.cursor/mcp.json
Claude Desktop (macOS): ~/Library/Application Support/Claude/claude_desktop_config.json
Windsurf: ~/.codeium/windsurf/mcp_config.json

Restart your AI assistant after saving. Full setup guide at docs.nablr.dev/quickstart.

Quick start

# Entry point — loads nablr context into your AI assistant
activate nablr

# Start a 14-day free trial (no credit card)
Start my nablr trial

# Invoke a persona
Set agent to developer

# Run a scanner
Scan this directory for technical debt

# Full SDLC workflow
Set agent to discovery  →  Set agent to architect  →  Set agent to developer

Personas

18 expert agents covering every SDLC phase: Discovery, Product Manager, QA Lead, Specifier, Architect, Developer, Tester, Test Designer, PR Reviewer, Scrum Master, Security Owner, Forensic Engineer, Strategist, Platform Engineer, Impact Architect, Migration Planner, Parity Tester, Cutover Engineer.

discovery and platform_engineer are permanently free.

Security

nablr makes exactly one category of outbound call: license validation to nablr-api.nablrco.workers.dev:443. Your code never leaves your machine.

Paid assets are pre-cached to ~/.nablr_cache/assets/ on activation — all subsequent prompt generation works fully offline.

# Verify no unexpected network calls
uv run python scripts/airgap_proof.py

Full security details at docs.nablr.dev/security.

License

Release files for nablr 4.14.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for nablr 4.14.1
File	Size	Uploaded
nablr-4.14.1.tar.gz	2.1 MB	Sep 12, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for nablr 4.14.1
File	Interpreter	ABI	Platform	Reset
nablr-4.14.1-py3-none-any.whl 883.3 kB Sep 12, 2026	Python 3	none	any	Details

Total release size: 3.0 MB

Release files / nablr-4.14.1.tar.gz

Download URL	nablr-4.14.1.tar.gz
Size	2.1 MB
Tags	Source
SHA-256 checksum How to use checksums	`2a2c77a2616a72a066e8ffcfd193d1670c7fb362727e6ee4c56c24f1a966990a`
BLAKE2b-256 checksum How to use checksums	`7374fd3bbc66b20cf3cd778f8d514dbdd8fd03edf498f2183212a8e8a521ef0f`
Upload date	Sep 12, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/nablrco/nablr
Publishing commit: github.com/nablrco/nablr/tree/cd4bd5607ec6a2832bdfb98f08d4efccee36eb41

Workflow

Publishing configuration: github.com/nablrco/nablr/blob/cd4bd5607ec6a2832bdfb98f08d4efccee36eb41/.github/workflows/publish.yml
Publishing logs: github.com/nablrco/nablr/actions/runs/34675548501/attempts/1

Artifact

Subject: nablr-4.14.1.tar.gz
SHA-256 checksum: 2a2c77a2616a72a066e8ffcfd193d1670c7fb362727e6ee4c56c24f1a966990a Verifying attestations

Release files / nablr-4.14.1-py3-none-any.whl

Download URL	nablr-4.14.1-py3-none-any.whl
Size	883.3 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`274d6f35f1a1ea1c4dcf838ea799a26229b2364f2b7b0b179f36538e3df69332`
BLAKE2b-256 checksum How to use checksums	`5f568152b50320efa8d72613743916e6bc2ecfc1218d73f801b6e705034f2847`
Upload date	Sep 12, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/nablrco/nablr
Publishing commit: github.com/nablrco/nablr/tree/cd4bd5607ec6a2832bdfb98f08d4efccee36eb41

Workflow

Publishing configuration: github.com/nablrco/nablr/blob/cd4bd5607ec6a2832bdfb98f08d4efccee36eb41/.github/workflows/publish.yml
Publishing logs: github.com/nablrco/nablr/actions/runs/34675548501/attempts/1

Artifact

Subject: nablr-4.14.1-py3-none-any.whl
SHA-256 checksum: 274d6f35f1a1ea1c4dcf838ea799a26229b2364f2b7b0b179f36538e3df69332 Verifying attestations