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

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.

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

The `execute_sql_query` tool 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.

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

Absolutely. Use the `get_model` tool 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.

MindsDB (AI Database & Predictors) MCP Server for Pydantic AI 6 tools — connect in under 2 minutes

Name: MindsDB (AI Database & Predictors)
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 6 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect MindsDB (AI Database & Predictors) through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to MindsDB (AI Database & Predictors) "
            "(6 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in MindsDB (AI Database & Predictors)?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About MindsDB (AI Database & Predictors) MCP Server

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.

Pydantic AI validates every MindsDB (AI Database & Predictors) tool response against typed schemas, catching data inconsistencies at build time. Connect 6 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

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

The MindsDB (AI Database & Predictors) MCP Server exposes 6 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect MindsDB (AI Database & Predictors) to Pydantic AI via MCP

Follow these steps to integrate the MindsDB (AI Database & Predictors) MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 6 tools from MindsDB (AI Database & Predictors) with type-safe schemas

Why Use Pydantic AI with the MindsDB (AI Database & Predictors) MCP Server

Pydantic AI provides unique advantages when paired with MindsDB (AI Database & Predictors) through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your MindsDB (AI Database & Predictors) integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your MindsDB (AI Database & Predictors) connection logic from agent behavior for testable, maintainable code

MindsDB (AI Database & Predictors) + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the MindsDB (AI Database & Predictors) MCP Server delivers measurable value.

Type-safe data pipelines: query MindsDB (AI Database & Predictors) with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple MindsDB (AI Database & Predictors) tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query MindsDB (AI Database & Predictors) and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock MindsDB (AI Database & Predictors) responses and write comprehensive agent tests

MindsDB (AI Database & Predictors) MCP Tools for Pydantic AI (6)

These 6 tools become available when you connect MindsDB (AI Database & Predictors) to Pydantic AI via MCP:

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

get_model

Get an explicitly trained AI prediction engine

get_status

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

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

list_views

List virtual data views stored inside a target project

Example Prompts for MindsDB (AI Database & Predictors) in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with MindsDB (AI Database & Predictors) immediately.

"List all ML models in the 'mindsdb' project"

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

"Show me all connected databases in my MindsDB instance"

Troubleshooting MindsDB (AI Database & Predictors) MCP Server with Pydantic AI

Common issues when connecting MindsDB (AI Database & Predictors) to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

MindsDB (AI Database & Predictors) + Pydantic AI FAQ

Common questions about integrating MindsDB (AI Database & Predictors) MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your MindsDB (AI Database & Predictors) MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.