How to Use the sevDesk MCP in AutoGen

Q: How can I check invoice details using sevDesk and AutoGen?

You initiate the process by calling getinvoice(invoiceid). Then, you introduce agents that debate whether the retrieved line items are accurate or if a related credit note needs to be checked via listcreditnotes.

Q: How do I list all parts available in sevDesk and AutoGen?

Start by having one agent call listparts. A second agent can then review that output, checking if the parts listed are active or if any need to be flagged for retirement based on internal rules.

Get consensus decisions on billing and CRM tasks using sevDesk and AutoGen's multi-agent debate framework.

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 AutoGen

Create your Vinkius account to connect sevDesk to AutoGen — 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Debate Billing Workflow Integrity

You don't just run `get_invoice`; you have agents debate the best way to process it. You can set up an 'Accounting Agent' and a 'Risk Agent.' The accounting agent calls `list_invoices`, but the risk agent challenges the results, flagging potential tax discrepancies or missing line items before finalization. This consensus-driven approach ensures no step is overlooked. It’s ideal when the answer requires checking multiple constraints across tools.

Resolve Complex Customer Account Issues

Handling a dispute needs more than one API call. You can have agents debate whether to issue a credit note using `get_credit_note`. One agent might flag the customer's payment history via `list_invoices`, while another argues for retaining strict billing standards based on their contract status retrieved from `get_contact`. The system converges on a decision after deliberation, which is crucial when dealing with high-stakes financial decisions.

Validate Parts and Supplier Relationships

Building a new product requires debate. One agent proposes adding the part via `create_part`, while another challenges it by running `list_parts` to ensure no duplicates exist, or checking `get_contact` data for proper supplier linkage. The multi-agent setup simulates peer review. If two agents disagree on whether a part should be created, you get a reasoned explanation for the conflict and how to resolve it.

Setup guide

Set up sevDesk MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes sevDesk tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="sevDesk_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent sevDesk data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="sevDesk_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent sevDesk data")
    print(result.messages[-1].content)

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 AutoGen

You initiate the process by calling `get_invoice(invoice_id)`. Then, you introduce agents that debate whether the retrieved line items are accurate or if a related credit note needs to be checked via `list_credit_notes`.

Yes. You can set up an agent pair: one retrieves all contacts using `list_contacts`, and the second validates if critical fields, like tax IDs, are present in the data retrieved by `get_contact`.

You can. Agents can debate an order's validity. One agent calls `list_orders`, another checks the associated parts using `get_part`, and a third validates if payment terms match existing credit notes.

This server touches financial records, specifically invoice details (invoice line items and tax). The agents' debate process forces consideration of these sensitive records before any action is taken.

Start by having one agent call `list_parts`. A second agent can then review that output, checking if the parts listed are active or if any need to be flagged for retirement based on internal rules.

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