Are API-created contacts exactly the same as UI-created ones?

Yes contextually. When you execute the `create_contact` function natively alongside `category` parameters (`3` stands for customer, `4` for typical suppliers), sevDesk anchors these entries officially inside the identical primary table. Be clear about whether it's an email-lead versus a firm.

Wait, does my generated API Token expire if left unused?

No. The verified 32-character hexadecimal key token possesses an infinite lifeline inherently tied directly, securely, and stubbornly to your primary login account. It decays or dies primarily upon deliberate manual revocation (regeneration) directly executed by you inside your dashboard user settings.

Can I fetch detailed line items from a single invoice ID using this agent?

Absolutely. Querying `list_invoices` outputs high-level paginated arrays, but invoking the precision extractor `get_invoice` fed deliberately with a target identifier ID unveils the core metadata array detailing isolated tax mappings, due-date boundaries, and intricate line items.

sevDesk MCP Server for Pydantic AI 15 tools — connect in under 2 minutes

Name: sevDesk
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 15 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect sevDesk through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to sevDesk "
            "(15 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in sevDesk?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About sevDesk MCP Server

Grant your conversational AI (like Claude or Cursor) the power of a dedicated German accounting clerk. The sevDesk MCP transforms your LLM into a sophisticated financial nexus capable of creating invoices, querying past-due credit notes, recording vouchers, and tracking your CRM endpoints dynamically. Stop wrestling with browser-based accounting dashboards and let your AI manage your bookkeeping automatically.

Pydantic AI validates every sevDesk tool response against typed schemas, catching data inconsistencies at build time. Connect 15 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Client & Supplier CRM Mastery — Read the entire client database via list_contacts, retrieve detailed metadata for specific IDs (get_contact), or seamlessly register brand new vendors via create_contact
Autonomous Invoicing & Orders — Fetch paginated ledger lists using list_invoices or list_orders, and delve deep into line items, calculated taxes, and due statuses directly using get_invoice and get_order
Inventory & Service Architecture — Monitor available billable components via list_parts, inspect standard pricing, and introduce novel catalog options autonomously via create_part
Accounting Governance — Keep strict tabs on your chart of accounts with list_accounting_types while verifying associated business inlets securely using list_bank_accounts
Voucher & Credit Auditing — Consolidate physical receipts through list_vouchers and trace structural adjustments flawlessly by scanning list_credit_notes

The sevDesk MCP Server exposes 15 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect sevDesk to Pydantic AI via MCP

Follow these steps to integrate the sevDesk MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 15 tools from sevDesk with type-safe schemas

Why Use Pydantic AI with the sevDesk MCP Server

Pydantic AI provides unique advantages when paired with sevDesk through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your sevDesk integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your sevDesk connection logic from agent behavior for testable, maintainable code

sevDesk + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the sevDesk MCP Server delivers measurable value.

Type-safe data pipelines: query sevDesk with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple sevDesk tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query sevDesk and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock sevDesk responses and write comprehensive agent tests

sevDesk MCP Tools for Pydantic AI (15)

These 15 tools become available when you connect sevDesk to Pydantic AI via MCP:

create_contact

Category 3 for customers, 4 for suppliers. Creates a new contact (customer or supplier) in sevDesk

create_part

Creates a new part or service in the catalog

get_contact

Retrieves details for a specific contact

get_credit_note

Retrieves details for a specific credit note

get_invoice

Retrieves details for a specific invoice, including line items and tax

get_order

Retrieves details for a specific order

get_part

Retrieves details for a specific part

list_accounting_types

Lists all accounting types (Chart of Accounts)

list_bank_accounts

Lists company bank accounts

list_contacts

Lists all contacts (customers, suppliers) in sevDesk

list_credit_notes

Lists all credit notes

list_invoices

Lists all invoices with embedded contact data

list_orders

Lists all sales orders

list_parts

Lists all parts (products and services) in the catalog

list_vouchers

Lists all vouchers (incoming/outgoing receipts)

Example Prompts for sevDesk in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with sevDesk immediately.

"Extract the details of invoice #18742 and summarize its line items alongside the associated contact name."

"List all currently existing bank accounts natively integrated using the core config."

Troubleshooting sevDesk MCP Server with Pydantic AI

Common issues when connecting sevDesk to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

sevDesk + Pydantic AI FAQ

Common questions about integrating sevDesk MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your sevDesk MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.