How to Use the sevDesk MCP in Pydantic AI

Q: How can I list all contacts in sevDesk using Pydantic AI?

You call listcontacts. Because this server is built with strict typing, your agent gets a guaranteed structure for every contact record it pulls from sevDesk.

Q: What data fields are available when listing invoices in sevDesk and Pydantic AI?

The listinvoices tool provides all the necessary invoice details, including embedded contact information. This structured output is validated by your agent against a strict schema.

Q: Can I check supplier data using sevDesk and Pydantic AI?

Yes. You use getcontact to pull specific records for suppliers, and the resulting object will always adhere to defined Python types. This makes your process reliable.

Q: How does the MCP Server handle accounting data integrity?

The server provides tools like listaccountingtypes and listbankaccounts. Pydantic validation ensures that when you read this financial context, the resulting object is always predictable.

Guarantee data integrity for your agent systems with Pydantic AI and sevDesk.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect sevDesk MCP to Pydantic AI

Create your Vinkius account to connect sevDesk to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup sevDesk with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Creating Contacts using the MCP Server

When you use `create_contact`, your agent writes a new record in sevDesk, but because of Pydantic validation, it *must* pass all required fields. This prevents half-formed data from entering your CRM. Retrieving details is just as safe; calling `get_contact` ensures that the output you get back matches an expected structure every single time.

Handling Financial Documents with Pydantic AI

The `list_orders` tool retrieves sales orders, and because of this MCP Server's design, your agent knows exactly what fields to expect. If sevDesk changes its structure, the failure is loud. Similarly, getting an invoice via `get_invoice` means you don't have to worry about unexpected JSON keys; they are validated against Pydantic models.

Cataloging Parts and Services with sevDesk MCP Server

The agent uses `list_parts` to pull the entire product catalog. If a part record is missing a required field (like a SKU), your system fails immediately, alerting you to data corruption. Checking individual items with `get_part` guarantees the structure of the returned object, making it reliable for production code.

Setup guide

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

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

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

You call `list_contacts`. Because this server is built with strict typing, your agent gets a guaranteed structure for every contact record it pulls from sevDesk.

The `list_invoices` tool provides all the necessary invoice details, including embedded contact information. This structured output is validated by your agent against a strict schema.

Yes. You use `get_contact` to pull specific records for suppliers, and the resulting object will always adhere to defined Python types. This makes your process reliable.

The server provides tools like `list_accounting_types` and `list_bank_accounts`. Pydantic validation ensures that when you read this financial context, the resulting object is always predictable.

The server exposes structured accounting data, including invoices (`get_invoice`), credit notes (`get_credit_note`), and sales orders (`list_orders`).

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