How to Use the BasicOps MCP in Pydantic AI

Q: What if the BasicOps server returns data that Pydantic AI doesn't expect?

Your code will raise a ValidationError immediately. The agent's operation stops, and you get a clear error message showing exactly what part of the data was wrong. This prevents data corruption.

Q: How do I get started with BasicOps and Pydantic AI?

First, pip install "pydantic-ai-slimmcp". Then, instantiate the MCPToolset with your Vinkius server URL and pass it to your Pydantic AI Agent. The tools will be available to your agent automatically.

Build reliable agents for BasicOps with Pydantic AI. Every API call is type-checked, so your automations don't break silently.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BasicOps MCP to Pydantic AI

Create your Vinkius account to connect BasicOps 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 BasicOps with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Prevent Bad Data with Pydantic

Pydantic AI's main job is to enforce correctness. When your agent calls `create_task` or `update_task`, Pydantic AI validates the response from the server against a strict schema. If a field is missing or has the wrong type, your code gets a `ValidationError` instantly. This means no silent failures. You won't find out three days later that half your tasks were created without a due date. Your agent either works correctly or it fails loudly, which is exactly what you want for anything doing real work.

Build Trustworthy Reports

When you ask an agent to build a project summary, you need to trust the data it pulls. With Pydantic AI, calls to `list_projects` and `list_project_tasks` return data that is guaranteed to match your Pydantic models. You can build internal dashboards without defensive coding. The agent can't hallucinate fields or misinterpret the API's response because the structure is locked in. This makes it simple to write follow-up code that processes the agent's output, because you know exactly what shape the data will be in every single time.

Use Any LLM with Pydantic AI

This MCP Server works with any model Pydantic AI supports. You can use OpenAI, Anthropic, Gemini, or even a local model running on your own machine. Pydantic AI standardizes the tool-use interaction, so the experience is the same. This frees you from vendor lock-in. You can build your agent's logic for interacting with BasicOps tools like `get_project` and `get_account_info` once. Then, you can swap out the underlying LLM to see which one gives you the best performance or cost, without rewriting any of your tool logic.

Setup guide

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

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

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

Pydantic AI gives you runtime validation. It ensures every piece of data from the BasicOps server matches your expected Python types, preventing bugs from API changes or unexpected responses. A direct client doesn't offer that.

Your code will raise a `ValidationError` immediately. The agent's operation stops, and you get a clear error message showing exactly what part of the data was wrong. This prevents data corruption.

Yes. Pydantic AI is model-agnostic. As long as you have a compatible adapter for your local model, you can use it to call BasicOps tools through the MCP toolset. The validation works the same way.

First, `pip install "pydantic-ai-slim[mcp]"`. Then, instantiate the `MCPToolset` with your Vinkius server URL and pass it to your Pydantic AI `Agent`. The tools will be available to your agent automatically.

It accesses your project, task, and team information. Pydantic AI's main security benefit is data integrity; its runtime validation acts as a contract, preventing malformed data from entering your system. This is on top of Vinkius's standard security, which isolates every request in a sandboxed environment with a single-use token.

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