MCP For Claude Marketplace
MindsDB (AI Database & Predictors)

MindsDB (AI Database & Predictors) MCP Connector for Claude

A+

Manage AI-powered data via MindsDB — execute SQL predictions, audit ML models, and connect data sources.

6 tools Official Updated Jun 28, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect your MindsDB instance to any AI agent and take full control of your machine learning workflows, automated predictions, and data integrations through natural SQL-based conversation.

What you can do

  • Predictive Orchestration — Execute arbitrary SQL statements to trigger automated machine learning commands, including 'CREATE MODEL' and 'SELECT ... PREDICT' directly from your agent
  • Model Lifecycle Audit — List trained AI tables (models) across your projects and retrieve detailed meta-features tracking generation progress or internal accuracy metrics
  • Data Source Integration — Enumerate external databases connected through MindsDB (e.g., PostgreSQL, Snowflake, ClickHouse) to audit your data pipeline boundaries securely
  • Virtual View Management — List virtual data views and SQL structural mappings that act as proxy tables for complex data transformation logic
  • Cluster Diagnostics — Retrieve active cluster status and version statistics to verify the availability and health of your MindsDB environment
  • Advanced SQL Execution — Run sophisticated queries combining scalar data with ML predictions to fetch literal insights across any schema entity natively

How it works

  1. Subscribe to this server
  2. Enter your MindsDB API URL and API Key (if using Cloud)
  3. Start automating your machine learning from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • Data Scientists — test predictor accuracy and monitor ML model training statuses through natural conversation without manual CLI tools
  • Software Developers — integrate AI-powered predictions into applications and verify data source connections directly from your workspace
  • BI Analysts — execute SQL queries that combine historical data with future predictions to generate rapid business insights efficiently
machine-learningsql-mlpredictive-analyticsmodel-deploymentdata-integration

6 tools expose this connector's capabilities to your AI agent.

list_databases

List external databases connected through MindsDB

list_models

Use when checking which algorithms are ready to query predictions. List trained AI tables (models) available in a project

get_model

Get an explicitly trained AI prediction engine

execute_sql_query

E.g: CREATE DATABASE, SELECT ... WHERE, CREATE MODEL ... PREDICT. Wrap logic safely. VERY IMPORTANT: queries returning a large number of rows MUST be explicitly wrapped in a LIMIT statement or risk hitting context overflow. Execute arbitrary SQL statements bounding MindsDB elements

list_views

List virtual data views stored inside a target project

get_status

Acts as a ping tracer returning valid core version/health specs. Get active cluster diagnostic and version statistics

See how to talk to your AI agent using MindsDB (AI Database & Predictors).

List all ML models in the 'mindsdb' project

I've retrieved your AI models from the 'mindsdb' project. Highlights include 'home_price_predictor' (Status: Complete), 'sales_forecaster' (Status: Training, 45%), and 'customer_churn_model'. Which one would you like to check the accuracy for?

Execute SQL: SELECT price, price_explain FROM mindsdb.home_price_predictor WHERE sqft = 2500

Executing prediction query… The predicted price for a 2500 sqft home is $450,000. Explanation: The model heavily weighted the square footage and recent neighborhood sales trends. Would you like to run this prediction for a different set of features?

Show me all connected databases in my MindsDB instance

I've identified 3 connected data sources: 'production_pg' (PostgreSQL), 'snowflake_warehouse' (Snowflake), and 'marketing_sheets' (Google Sheets). I can list the available tables for any of these sources if you'd like.

Yes. Use the `execute_sql_query` tool 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.

Related Connectors

LE

LearningSuite MCP

10 tools Official

Create and deliver corporate training programs with course authoring, quizzes, and progress tracking for distributed teams.

A+ View details →
GL

Glama MCP

8 tools Official

Connect your AI agent to the Glama directory. Discover MCP servers dynamically, analyze attributes, and proxy external intelligence networks through a unified gateway natively.

A+ View details →
AR

Arweave MCP

13 tools Official

Interact with the Arweave permaweb — query network info, check wallet balances, inspect transactions, and calculate storage costs directly from your AI agent.

A+ View details →
X<

XML <-> JSON Converter MCP

2 tools Official

Parse legacy systems easily. Deterministically convert massive XML, SOAP, or RSS feeds into clean JSON (and back) without LLM hallucinations.

A+ View details →