How to Use the MindsDB (AI Database & Predictors) MCP in Pydantic AI

Q: Can I inspect virtual views in MindsDB (AI Database & Predictors) with Pydantic AI?

Yes, your agent uses listviews to retrieve virtual views, which are parsed into typed Python objects. This allows the agent to build correct, validated SQL queries.

Get type-safe, runtime-validated predictive SQL queries for your Pydantic AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

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

Create your Vinkius account to connect MindsDB (AI Database & Predictors) to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup MindsDB (AI Database & Predictors) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe SQL execution in Pydantic AI

The `execute_sql_query` tool executes predictive and analytical SQL commands with strict runtime validation. The MCP Server ensures all database transactions are securely processed. To prevent validation failures from massive datasets, you must instruct the agent to use explicit LIMIT clauses. This keeps the returned rows within bounded memory limits.

Validated model metadata auditing

The `list_models` tool fetches the active machine learning models, returning a validated list of predictors to the agent. If the agent needs to inspect a specific algorithm, it calls `get_model` to retrieve its parameters. Because Pydantic AI enforces type safety, any schema mismatch in the model's metadata triggers an immediate validation error. This prevents your agent from making decisions based on malformed model outputs.

Schema inspection and cluster diagnostics

The `list_databases` tool exposes connected databases, and `list_views` lists the virtual data views stored in your projects. The agent reads these schemas to construct valid SQL queries without guessing table structures. For system monitoring, the `get_status` tool provides validated cluster version and health metrics. If the MCP connection experiences latency, the agent detects it.

Setup guide

Set up MindsDB (AI Database & Predictors) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "mindsdb-ai-database-predictors-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to MindsDB (AI Database & Predictors) tools.",
)

result = await agent.run("List recent MindsDB (AI Database & Predictors) transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by MindsDB. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect MindsDB (AI Database & Predictors) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about MindsDB (AI Database & Predictors) MCP in Pydantic AI

The framework intercepts all tool outputs and validates the returned SQL rows and model metadata against Pydantic schemas at runtime. This guarantees that your agent never processes malformed database responses.

You instantiate the connection using the toolset class with your MCP Server HTTP endpoint. You then pass this toolset directly into the agent's toolsets parameter.

Yes, your agent uses `list_views` to retrieve virtual views, which are parsed into typed Python objects. This allows the agent to build correct, validated SQL queries.

Yes, the toolset supports both streamable HTTP and SSE transports. You can run the server externally and connect your agent securely over either protocol.

All SQL query strings, model parameters, and database schemas are processed within an isolated V8 sandbox. This ephemeral execution environment ensures that sensitive table rows and predictor configurations are never cached or exposed outside your secure session.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript