How to Use the Evoliz MCP in Pydantic AI

Q: How do I connect Evoliz to Pydantic AI?

Install the pydantic-ai-slimmcp package via pip. Create an MCPToolset pointing to your HTTP URL and pass it in the toolsets array of your Agent.

Integrate the Evoliz MCP Server with Pydantic AI to enforce strict runtime validation on your French accounting and invoicing workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Evoliz MCP to Pydantic AI

Create your Vinkius account to connect Evoliz 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 Evoliz with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Accounting Operations

The `list_invoices` and `list_quotes` tools pull your billing history into your Python application. Pydantic AI validates every single field in the response against your defined models before the agent can even look at it. If the Evoliz API returns an unexpected data type, the framework fails loudly. You get a clear validation error instead of silent corruption, guaranteeing your financial data stays perfectly structured.

Client Management via Pydantic AI

The `create_client` tool gives your agent the ability to write new customer records to your database. It requires a name and a specific type, which the agent formats as a validated JSON object. You verify these creations instantly using `get_client` or `list_clients`. Because the framework is model-agnostic, you run these operations using local models, Anthropic, or OpenAI without changing your code.

Connect the Evoliz MCP Server

The `get_article` and `list_articles` tools expose your product catalog to your agent. Your application fetches specific items or paginates through the entire list to sync pricing data. Setup requires installing the `pydantic-ai-slim[mcp]` package. You initialize an `MCPToolset` with your HTTP endpoint and pass it to your Agent. The unified approach handles the transport layer automatically.

Setup guide

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

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

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

Install the `pydantic-ai-slim[mcp]` package via pip. Create an `MCPToolset` pointing to your HTTP URL and pass it in the `toolsets` array of your Agent.

The framework throws a validation error immediately. It checks the response against your Pydantic models at runtime, preventing hallucinated fields from entering your system.

The current toolset focuses on retrieval and client creation. Your agent reads billing data using `get_invoice` and adds customers using `create_client`.

Pydantic AI is completely model-agnostic. You use OpenAI, Gemini, Anthropic, or local models to execute these accounting tools.

Auth is handled at the platform level so you never expose raw API keys to your code. Your quotes and invoices are processed in an isolated V8 environment that spins down the moment the request completes.

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