How to Use the Aiven MCP in Pydantic AI

Q: How do I register Aiven with Pydantic AI?

Use the MCPToolset constructor with your managed server URL. Pass this instance into the toolsets argument when initializing your Pydantic AI Agent. The framework automatically extracts the schemas for all 30 tools.

Q: Can Pydantic AI manage Aiven billing groups?

Yes, the agent can call listbillinggroups and listbillinggroupinvoices to gather cost metrics. The returned billing data is fully validated against defined schemas, making it easy to feed into downstream accounting scripts.

Build type-safe database automation in Pydantic AI with validated Aiven tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aiven MCP to Pydantic AI

Create your Vinkius account to connect Aiven 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 Aiven with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe database provisioning

The `create_service` tool provisions managed databases with strict validation of all input parameters. Pydantic AI ensures that service plans, project names, and cloud regions conform to exact schemas before hitting the API. If your agent attempts to configure an invalid database type, the system catches the error at runtime. This prevents broken API calls and ensures that only valid configuration objects are processed by the server.

Validated project and VPC management

The `create_project` tool builds isolated environments that are verified against strict Pydantic schemas. Your agent can safely run `create_project_vpc` knowing that the network configurations are typed and validated. Let's look at the logs. When querying `list_project_vpcs`, the returned network metadata is parsed into structured Python models. This eliminates the risk of your agent misinterpreting raw JSON payloads.

Secure account auditing via Pydantic AI

The `list_accounts` tool retrieves all cloud accounts accessible by your current API credentials. The agent uses `list_account_projects` to map out the entire resource tree under each account. Here's the thing: parsing unstructured cloud data leads to agent hallucinations. By forcing all responses through strict schemas, your agent always gets clean, predictable lists of projects and services.

Setup guide

Set up Aiven 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": {
        "aiven-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Aiven 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 Aiven. 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 Aiven 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 Aiven MCP in Pydantic AI

Use the `MCPToolset` constructor with your managed server URL. Pass this instance into the `toolsets` argument when initializing your Pydantic AI Agent. The framework automatically extracts the schemas for all 30 tools.

The framework will raise a validation error and fail loudly. This prevents your agent from acting on corrupt or incomplete infrastructure state. It is a major safety advantage over untyped frameworks.

Yes, the agent can call `list_billing_groups` and `list_billing_group_invoices` to gather cost metrics. The returned billing data is fully validated against defined schemas, making it easy to feed into downstream accounting scripts.

The server returns standard HTTP rate limit headers when the API is busy. Your agent can catch these exceptions and implement a backoff strategy to retry the failed tool calls safely.

Your API tokens and account details are stored securely as environment variables and never exposed to the LLM. The server only uses them to sign requests to the cloud provider. No credential data is ever cached or persisted on the host system.

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