• CONTEXT
  • LOGIC
  • ACCURACY
  • HUMAN

How to query Ninox database schema with your AI

Connect your AI to your Ninox databases once. After that, your agent understands your tables, fields, and relationships.

Ask AI about this page

Short answer

How can I let my AI see my Ninox database structure?

Your AI uses the Ninox MCP to pull your table lists and field definitions. This gives your agent the context it needs to understand your relational data layout.

The outcomes

What your AI achieves

The AI uses your schema to bridge the gap between natural language and your specific data structure.

CONTEXT

Mapping your data

The AI identifies every table and field in your Ninox setup. It learns how your records are organized.

LOGIC

Understanding relations

By reading the schema, your agent sees how different tables link together. This prevents errors when asking for related data.

ACCURACY

Validating queries

The AI checks field names against your actual schema. You get responses that match your real database structure.

HUMAN

Manual oversight

You decide which databases to expose. The AI only sees what the tools allow it to see.

The workflow

What your AI does when the schema request arrives.

The AI follows a specific sequence to build a mental map of your Ninox environment.

  1. Find your databases

    The AI looks for all available Ninox databases linked to your account.

    list_databases

  2. Inspect the structure

    Once a database is selected, the AI pulls the full list of tables and field definitions.

    get_database_schema

  3. Map relationships

    The agent analyzes how fields connect across different tables to understand your relational model.

    get_database_schema

  4. Prepare for queries

    The AI uses this structural knowledge to interpret your natural language requests into valid data lookups.

    get_database_schema

Try it

Copy these to start.

Use these prompts to begin interacting with your Ninox data.

Starting points

These are opening lines. Swap out the database names for your actual Ninox database titles.

Ninox Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_PXJrbeq9A0WnBpVI6VWgAL2icGxZ55Dkrrumb7Lc/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Ninox capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "ninox-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_PXJrbeq9A0WnBpVI6VWgAL2icGxZ55Dkrrumb7Lc/mcp"
    }
  }
}
Copy into chat04

  • List all my Ninox databases so I can see what's available.

  • Show me the schema for my 'Client Management' database.

  • What are the field names in the 'Invoices' table?

  • Explain the relationship between the 'Projects' and 'Tasks' tables in my database.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Ninox once, then ask.

One connection links your Ninox account to your AI client. Your credentials stay encrypted and secure on our side.

Connect Ninox to your AI

FAQ

How this task behaves

  • 01

    Can the AI change my Ninox field names?

    No. The tools provided only allow the AI to read the schema, not modify it.

  • 02

    Does the AI see all my data immediately?

    No. The AI first sees the structure, such as tables and fields. It only accesses specific record data when you ask it to.

  • 03

    Can I restrict which databases the AI can see?

    The AI can only see the databases you have authorized through the connection.

  • 04

    Will the AI delete any of my tables?

    No. This specific task is read-only. The AI cannot delete or alter your database structure.

  • 05

    How does the AI know which field is a link to another table?

    The schema tool provides the field definitions, which include the relational metadata the AI needs to understand those links.

  • More questions about Ninox? The Connector page answers them. See everything the Ninox Connector can do

Connect Ninox to Claude, Cursor, ChatGPT & more