How to Use the MyScale (SQL Vector Database API) MCP in Pydantic AI

Q: How do I use MyScale (SQL Vector Database API) with Pydantic AI for type-safe search?

Use vectorsearch as a tool in your Pydantic AI agent. The results are parsed and validated against your Pydantic models automatically.

Q: Can Pydantic AI track index status on MyScale (SQL Vector Database API)?

Yes. The checkindexstatus tool returns a structured response that Pydantic AI can validate, ensuring you know exactly when the build finishes.

Q: How do I ensure my database connection is healthy?

Use pingcluster as a pre-check tool. It's a simple way to verify connectivity before the agent starts executing complex tasks.

Type-safe vector database operations for 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 MyScale (SQL Vector Database API) MCP to Pydantic AI

Create your Vinkius account to connect MyScale (SQL Vector Database API) 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 MyScale (SQL Vector Database API) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe SQL queries in Pydantic AI

Pydantic AI needs strict schemas. Use `execute_sql_query` and trust the return types, as the tool output is validated against your models at runtime. Stop worrying about silent failures. If the SQL returns a malformed row, the agent catches it immediately, preventing corrupt data from entering your context window.

Verified index management for Pydantic AI

Manage your vector indices with `create_vector_index` and `check_index_status` while maintaining full type safety. The agent validates the status response before proceeding. Your agent will only move forward when the index is confirmed ready. This ensures your Pydantic AI agent doesn't try to search an uninitialized index.

Type-checked vector search in Pydantic AI

Run `vector_search` and let Pydantic AI handle the result validation. You get a clean, typed object back, ready for use in your application logic. This removes the guesswork. By forcing validation on the search output, you ensure every vector found matches the expected schema defined in your Pydantic models.

Setup guide

Set up MyScale (SQL Vector Database API) 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": {
        "myscale-sql-vector-database-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to MyScale (SQL Vector Database API) tools.",
)

result = await agent.run("List recent MyScale (SQL Vector Database API) 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 MyScale. 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 MyScale (SQL Vector Database API) 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 MyScale (SQL Vector Database API) MCP in Pydantic AI

Use `vector_search` as a tool in your Pydantic AI agent. The results are parsed and validated against your Pydantic models automatically.

Yes. The `check_index_status` tool returns a structured response that Pydantic AI can validate, ensuring you know exactly when the build finishes.

Yes. Every tool response is JSON, which Pydantic AI treats as a source for its runtime validation logic.

Use `ping_cluster` as a pre-check tool. It's a simple way to verify connectivity before the agent starts executing complex tasks.

The server functions as a stateless proxy. It processes your SQL and vector data in memory and discards it after the response is sent to your agent.

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

Mastra AI sdk-typescript

Start using the MyScale (SQL Vector Database API) MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started