Let AI agents propose database changes. You review and merge.
Connect any MCP-capable agent — Claude Code, Cursor, VS Code. Every change it proposes becomes a reviewable request you approve before it touches your database.
Propose → Review → Apply
The agent proposes
Your agent connects to nuzur's MCP server. When it wants to add a table, alter a column, or backfill data, it doesn't execute anything — it creates a change request.
You review the diff
See exactly what will change: schema and data, side by side, before and after. Not a wall of SQL in a chat window — a structured diff against your actual model. Leave it in draft, edit it, or reject it.
Approve and apply
One click applies the change through nuzur — migration generated, executed, versioned. Full history of every change, who (or what) proposed it, and who approved it.
The part nobody else does: change requests cover data changes too, not just schema. "Backfill the category column for 40,000 rows" gets the same review-before-apply treatment as CREATE TABLE.
The agent never holds the pen
nuzur is model-first: your database schema lives as a versioned model, and every change — human or agent — goes through it. That's what makes agent access safe by construction rather than by prompt engineering.
No direct write access
The agent's credentials can propose, not execute. There is no prompt injection that gets around a permission that doesn't exist.
Versioned everything
Every applied change request is a version you can inspect and trace. Your schema history reads like a git log.
Human-authored changes too
The same review flow works for your teammates. Agents just made it urgent.
Modern visual editor
Create and edit complex models with our intuitive drag-and-drop editor, featuring version control and collaboration tools.
- Nested JSON structures as first class citizens
- Extended field types and validations
- Generate SQL migrations, Protobuf, and Go server code from your schema
- Change request review workflow
- AI Assistant to help create and manage models
Robust data manager
Easily manage datasets associated with your models, featuring field validations, local database connections, and change request reviews.
- Intuitive data grid interface
- Field-level validations
- Connect to local databases via local agent
- Change request review workflow
- AI Assistant to help create and edit queries
Code generation
From your model, nuzur generates clean, production-ready Go — plus SQL migrations, Protobuf APIs, and everything needed to deploy, regenerated as your schema evolves.
- High-performance Go gRPC with type-safe sqlc queries — no ORM bloat
- SQL migrations, native MySQL & PostgreSQL
- Built-in JWT / Keycloak auth, caching, and modular Uber Fx wiring
- Dockerfile, Helm & CI/CD, plus AI-ready context (AI.md) for Cursor and Claude
Local Agent
Pair your machine as a local agent to query your local databases directly from the nuzur Data Manager — no cloud credentials needed.
- Pair any machine as a local database agent via the CLI
- Query local MySQL and PostgreSQL databases
- No cloud credentials required — traffic stays local
Team collaboration
Assign roles and permissions to team members, track changes, and collaborate seamlessly on models and data with change requests.
- Change tracking and history
- User roles and permissions
- Team and project level access controls
Additional Features
CLI
Run local agents, generate code with extensions, and manage your nuzur projects from the terminal. Available for macOS, Linux, and Windows.
Extension SDK
Build custom extensions to enhance nuzur's functionality.
SQL Support
MySQL and PostgreSQL databases are natively supported.
Give your agent a seatbelt
Stop choosing between "agent with prod access" and "human clipboard."
Connect your agent — freeSolo founder here — if setup takes you more than 5 minutes, reach out and I'll do it with you.