How to Use the sevDesk MCP in LangChain

Q: How do I find invoice details using sevDesk and LangChain?

You can call getinvoice(invoiceid) directly. If you need to check all historical invoices, use listinvoices first to get a list of IDs, then feed those into your chain for detailed processing.

Q: Does sevDesk and LangChain support checking supplier details?

Yes. You can use listcontacts to pull all contacts (including suppliers), or call getcontact(contactid) if you know the specific ID. The agent handles filtering for you.

Q: How do I list all sales orders in sevDesk and LangChain?

The simplest way is to call listorders(). This returns a paginated list of all records. You can then pass the IDs from this list into subsequent steps for detailed analysis.

Build multi-step financial automation and reasoning chains with sevDesk and LangChain.

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 LangChain

Create your Vinkius account to connect sevDesk to LangChain — 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automate Complex Accounting Workflows

You can build full accounting cycles by chaining tools together. For instance, an agent can first use `list_orders` to check open sales orders, then call `get_invoice` for the specific invoice ID, and finally validate necessary tax rates using `list_accounting_types`. This sequence allows your agent to decide which tool to run next based on the output. It's perfect when you need an outcome that requires multiple steps: check inventory with `list_parts`, then create a record with `create_contact`.

Manage Multi-Stage Customer Interactions

Handling customer records isn't just one API call. You can write chains that first retrieve contact details using `get_contact`, check their payment history with `list_invoices`, and if necessary, generate a new credit note via `get_credit_note`. This flow lets your agent adapt to the situation. It might use `list_contacts` to find an existing user, then decide whether they need a service record (`create_part`) or just a simple data fetch.

Systematic Inventory and Catalog Maintenance

Keep your product catalog clean using multi-tool chains. Start by listing all available parts with `list_parts`. Then, if you detect a new service offering, the chain can call `create_part` to add it immediately. The agent manages these dependencies automatically. Need to update supplier data? The workflow can first list all contacts (`list_contacts`), and then use `get_contact` for specific validation before writing any changes.

Setup guide

Set up sevDesk MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes sevDesk tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "sevdesk-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent sevDesk transactions"
    })
    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 LangChain

You can call `get_invoice(invoice_id)` directly. If you need to check all historical invoices, use `list_invoices` first to get a list of IDs, then feed those into your chain for detailed processing.

Yes. You can use `list_contacts` to pull all contacts (including suppliers), or call `get_contact(contact_id)` if you know the specific ID. The agent handles filtering for you.

Absolutely. Since it's a framework client, your agent can decide which tool to call next based on the output of the previous one. This means you aren't limited to single transactions.

This server touches contact information, including names and addresses (the contact data type). When building your chains, remember that the agent processes this sensitive user data.

The simplest way is to call `list_orders()`. This returns a paginated list of all records. You can then pass the IDs from this list into subsequent steps for detailed analysis.

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