How to Use the Curve Fitting Engine MCP in Pydantic AI

Q: How do I add the Curve Fitting Engine toolset to a Pydantic AI agent?

Install pydantic-ai-slimmcp, then instantiate an MCPToolset with your Vinkius server URL. You pass this object into the toolsets list when you create your Agent.

Q: What happens if the server returns data that doesn't match my Pydantic model?

Pydantic AI will raise a ValidationError immediately and halt execution. Your agent won't proceed with corrupt or unexpected data, which is the main reason to use this framework.

Add type-safe, mathematically exact curve fitting to your Pydantic AI agent. No bad data, guaranteed.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Curve Fitting Engine MCP to Pydantic AI

Create your Vinkius account to connect Curve Fitting Engine 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 Curve Fitting Engine with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Crash-Proof Data Validation

This server's `calculate_regression` tool returns a structured response with coefficients and an equation. Pydantic AI automatically validates this response against a Pydantic model at runtime. If the server ever sends back malformed data—a typo in the equation, a string instead of a float—your agent will raise a `ValidationError` instantly. This stops data corruption cold. You can trust the data your agent is working with.

Use Any Model, Get Consistent MCP Server Results

Pydantic AI is model-agnostic, and so is this MCP server. You can swap between OpenAI, a local model, or anything else, and your agent's ability to perform curve fitting remains unchanged. The tool's output is always the same. The combination is powerful. The LLM handles the 'when' of calling the tool, but the tool itself provides a stable function. Pydantic's validation is the final guarantee that the result is correct, regardless of the model.

A Source of Mathematical Truth

Your agent needs ground truth. The `calculate_regression` tool provides it. It doesn't approximate or hallucinate a best-fit line; it calculates the mathematically perfect linear or polynomial regression for the data you provide. This gives your Pydantic AI agent a reliable function to call when it needs a real number or a precise equation. It's the difference between asking an intern to eyeball a chart and having a calculator that gives you the right answer every time.

Setup guide

Set up Curve Fitting Engine 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": {
        "curve-fitting-engine-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Curve Fitting Engine 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 ml-regression. 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 Curve Fitting Engine 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 Curve Fitting Engine MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]`, then instantiate an `MCPToolset` with your Vinkius server URL. You pass this object into the `toolsets` list when you create your `Agent`.

Pydantic AI will raise a `ValidationError` immediately and halt execution. Your agent won't proceed with corrupt or unexpected data, which is the main reason to use this framework.

Yes. The Curve Fitting Engine is an MCP tool, so it works independently of the LLM. Your Pydantic AI agent can use any model you configure—OpenAI, Anthropic, local, etc.—to decide when to call the tool.

An LLM can only guess at a regression. The Curve Fitting Engine provides a mathematically exact answer. Pydantic AI then ensures that this correct answer is delivered to your agent in a perfectly structured, type-safe object.

Yes. Your agent sends the raw scatter plot data to the Vinkius server, which runs in a zero-trust, ephemeral sandbox. Then, Pydantic's validation happens on your client-side, adding a layer of data integrity checking on your machine before the agent even touches the result.

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