An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Mindsdb AI Database Predictors to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Run machine learning models using standard SQL commands.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 6 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through MindsDB.

  1. 01

    Execute SQL query

    This capability runs any SQL command you send, including model creation and prediction queries. You should always use a LIMIT clause for large datasets to avoid overwhelming your AI client.

  2. 02

    List models

    This capability retrieves a list of all trained AI models available in your current project.

  3. 03

    List databases

    This capability shows you all the external databases currently connected to your MindsDB instance.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through MindsDB.

  1. 04

    Get status

    This capability provides diagnostic information and version stats to check your cluster health.

  2. 05

    Get model

    This capability fetches specific details about a single, trained AI prediction engine.

  3. 06

    List views

    This capability pulls a list of virtual data views that act as proxy tables for your data transformations.

Real work

What teams actually run

01

Automated Forecasting

Run SQL queries that combine your existing data with trained models to predict future sales or trends.

02

Model Lifecycle Management

Check which models are finished training and which are still in progress using simple list commands.

03

Data Source Verification

Confirm that your external PostgreSQL or Snowflake connections are active and accessible.

04

Rapid Prototyping

Test how a new model performs on specific data rows by running targeted prediction queries.

Automate a task

Put MindsDB to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

MindsDB works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put MindsDB to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

865ms average. Fast in production.

MindsDB is checked daily against the live service.

Daily averagePeak 1220ms
Oct 3Today
Fastest day
640ms
Slowest day
1220ms
14-day trend
Slowing+38%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of MindsDB, so you can see the experience inside your AI.

It does not authenticate your account with MindsDB. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

MindsDB Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_wo8z4btUozCcWNcaSyNerjmMILAoiY0Mm4LOh9m9/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 — MindsDB capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "mindsdb-ai-database-predictors-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_wo8z4btUozCcWNcaSyNerjmMILAoiY0Mm4LOh9m9/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up MindsDB in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work MindsDB owners hand off.

This MCP is built for technical users who want to bridge the gap between raw data and machine learning via SQL.

  • 01

    Data Scientists

    They use the agent to monitor model training status and test predictor accuracy without using a CLI.

  • 02

    Software Developers

    They integrate ML predictions into their apps by verifying data connections and running queries from their workspace.

  • 03

    BI Analysts

    They combine historical data with future predictions using SQL to generate business insights.

FAQ

Questions MindsDB owners ask.

  • 01

    How do I use this MCP with Claude?

    You simply connect your Claude client to the Vinkius-hosted MCP. Once connected, you can talk to Claude to execute SQL queries or manage your MindsDB models.

  • 02

    Can I run custom SQL queries?

    Yes, you can use the execute_sql_query capability to run any valid SQL statement, including model creation and data selection.

  • 03

    What happens if my query returns too much data?

    You should always wrap queries that return many rows in a LIMIT statement to prevent hitting the context limits of your AI client.

  • 04

    Which databases can I connect to MindsDB?

    MindsDB supports various external sources like PostgreSQL, Snowflake, and ClickHouse, which you can manage through this MCP.

  • 05

    Do I need to host the MCP myself?

    No, Vinkius hosts and manages the MCP for you. You just provide your credentials and connect your client.

  • 06

    Can I train a machine learning model using SQL through my agent?

    Yes. Use the execute_sql_query capability with the 'CREATE MODEL' statement. Your agent will dispatch the command to MindsDB, which will automatically handle the data processing and training of your predictor asynchronously.

  • 07

    How do I connect an external database like PostgreSQL to MindsDB using the agent?

    The execute_sql_query capability supports the 'CREATE DATABASE' syntax. You can command your agent to link a new data source by providing the connection parameters, allowing MindsDB to query your existing data natively.

  • 08

    Can my agent retrieve the status of an ongoing model training?

    Absolutely. Use the get_model capability by providing the model name and project. Your agent will report the current training state, accuracy metrics, and any errors encountered during the AI generation process.

Explore

More in Loved By Devs

Suggestions

Connect MindsDB to Claude, Cursor, ChatGPT & more