4,500+ servers built on MCP Fusion
Vinkius

sevDesk MCP. Manage invoices, contacts, and orders with AI.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

sevDesk MCP on Cursor AI Code Editor MCP Client sevDesk MCP on Claude Desktop App MCP Integration sevDesk MCP on OpenAI Agents SDK MCP Compatible sevDesk MCP on Visual Studio Code MCP Extension Client sevDesk MCP on GitHub Copilot AI Agent MCP Integration sevDesk MCP on Google Gemini AI MCP Integration sevDesk MCP on Lovable AI Development MCP Client sevDesk MCP on Mistral AI Agents MCP Compatible sevDesk MCP on Amazon AWS Bedrock MCP Support

Just plug in your AI agents and start using Vinkius.

sevDesk MCP Server gives your AI agent direct read and write access to sevDesk's core data. You can manage contacts, create sales orders, draft invoices, and track accounting records—all without opening a browser dashboard.

It connects your LLM to CRM functions, parts catalogs, bank accounts, and the full ledger history for autonomous financial management.

What your AI agents can do

Create contact

Adds a new customer or supplier record to sevDesk.

Create part

Creates a brand-new product or service entry in the catalog.

Get contact

Retrieves all specific details about one contact ID.

+ 12 more capabilities included
Manage Customer Records

The agent can list, read details for, or create new customer or supplier entries.

Generate Invoices and Orders

It retrieves full invoice line items, tax breakdowns, and order statuses needed for billing reports.

Maintain Catalog Parts

You can list existing parts or services and create entirely new entries in the product catalog.

Audit Accounting Data

The agent lists your bank accounts, views available accounting types, and checks vouchers/credit notes for reconciliation.

View Core Financial Lists

It pulls comprehensive, paginated lists of all contacts, invoices, orders, parts, and more.

Supported MCP Clients

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients
Free for Subscribers

Waiting for input…

AI Agent

sevDesk MCP Server: 15 Tools for Financial Management

These tools allow your AI client to read, write, and manage all core financial records in sevDesk, including contacts, invoices, parts, and bank accounts.

create019d7606

create contact

Adds a new customer or supplier record to sevDesk.

create019d7606

create part

Creates a brand-new product or service entry in the catalog.

get019d7606

get contact

Retrieves all specific details about one contact ID.

get019d7606

get credit note

Pulls the full data record for a single credit note.

get019d7606

get invoice

Gets detailed information about one invoice, including all line items and taxes.

get019d7606

get order

Retrieves the full details of a specific sales order.

get019d7606

get part

Gets detailed information for one part or service ID.

list019d7606

list accounting types

Displays the entire chart of accounts structure used by the company.

list019d7606

list bank accounts

Lists all bank accounts connected to the system for reference.

list019d7606

list contacts

Retrieves a complete list of every customer and supplier in sevDesk.

list019d7606

list credit notes

Lists all recorded credit notes for auditing purposes.

list019d7606

list invoices

Provides a comprehensive list of all invoices, including contact data.

list019d7606

list orders

Displays a full list of all sales orders placed.

list019d7606

list parts

Lists every product and service available in the catalog for sale.

list019d7606

list vouchers

Pulls a list of all incoming or outgoing physical receipts/vouchers.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

  • Import from OpenAPI, Swagger, or YAML specs
  • Create Agent Skills with progressive disclosure
  • Deploy to edge with MCPFusion framework
  • Built in DLP, auth, and compliance on every call
  • Real time usage dashboard and cost metering
  • Publish to catalog or keep private
Start building

Make Your AI Do More

Start with sevDesk, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.

  • Use this MCP plus 4,700+ others, all in one place
  • Add new capabilities to your AI anytime you want
  • Every connection is secured and compliant automatically
  • Track usage and costs across all your servers
  • Works with Claude, ChatGPT, Cursor, and more
  • New servers added to the catalog every week

What you can do with this MCP connector

sevDesk MCP Server: Your AI Agent's Financial Copilot

This server gives your AI agent direct read and write access to sevDesk’s core financial records. You won't need to open a browser dashboard or fight through menus; your agent handles bookkeeping tasks—from generating invoices to tracking bank balances—by talking straight to the underlying API.

Managing Customer & Vendor Records

To handle client and vendor data, your agent first uses list_contacts to grab a complete list of every customer and supplier. If you need specifics on just one person or company, it pulls all the necessary details using get_contact. When a new client signs up or a new vendor drops in, your agent adds them instantly with create_contact, keeping your books current.

Generating Orders and Invoices

The agent handles everything related to billing. To generate reports or check payment status, it uses list_invoices for a comprehensive list of every invoice, including the contact details. For deep dives into any single bill, get_invoice retrieves detailed information, showing all line items and tax breakdowns. Similarly, if you need an order's history, list_orders provides a full roster of sales orders placed, and get_order pulls every detail for one specific sale.

Maintaining the Product Catalog

Need to keep track of what you sell? Your agent lists all existing parts or services using list_parts. If you find yourself with new inventory or a service offering, it creates a brand-new entry in the catalog via create_part, maintaining accurate pricing and descriptions. For checking specifics on an item already listed, it uses get_part to pull detailed information for any given part or service ID.

Auditing Accounting Data

When you gotta reconcile numbers, your agent has the tools. It lists all bank accounts connected to the system using list_bank_accounts, so you always know where the dough is sitting. To understand how your company classifies money, it displays the entire chart of accounts structure with list_accounting_types. For internal tracking and reconciliation, the server lets your agent check incoming or outgoing physical receipts/vouchers via list_vouchers or pull a full data record for any credit note using get_credit_note, while also listing all recorded notes with list_credit_notes.

Core Data Retrieval

For quick overviews, the agent can list everything: it pulls comprehensive, paginated lists of contacts (list_contacts), invoices (list_invoices), orders (list_orders), parts (list_parts), and vouchers (list_vouchers). This gives your AI client a complete picture without ever opening a browser.

How sevDesk MCP Works

  1. 1 Install this module directly into your MCP-compatible IDE or conversational context.
  2. 2 Inject your 32-character hexadecimal sevDesk API Token to establish a secure connection.
  3. 3 Prompt your agent with natural language instructions (e.g., "What's the total for invoice #123?").

The bottom line is, your AI client executes multiple required accounting actions through specific, named tools without you ever touching a dashboard.

Who Is sevDesk MCP For?

This is for the finance team member who gets frustrated trying to cross-reference data across five different sevDesk tabs. It's for the solopreneur whose AI agent needs to handle bookkeeping tasks automatically, or the auditor who has to reconcile physical receipts against digital records every month. Stop copy-pasting IDs; let your agent do it.

Freelance Consultant

Uses the agent to draft new client records using create_contact and immediately query pending invoice tallies via list_invoices.

Agency Bookkeeper

Instructs the AI to cross-reference registered parts (list_parts) against generated credit notes (list_credit_notes) for a quarterly audit check.

Small Business Owner

Asks their agent to list all connected bank accounts (list_bank_accounts) and verify the current accounting categories using list_accounting_types.

What Changes When You Connect

  • Automated Data Retrieval: Instead of navigating to the invoicing tab, searching by customer name, and then downloading a PDF, you just ask your agent. The tool get_invoice pulls all line items, taxes, and due dates directly into your chat window for immediate review.
  • Full Lifecycle Management: You can track an order from start to finish. First, check the sales order with list_orders, then use get_order to verify parts, and finally confirm billing by calling get_invoice. The agent manages this sequence automatically.
  • Zero-Click CRM Updates: Creating a new vendor used to mean logging into another system. Now, you just ask the AI to create the contact using create_contact, and it handles the record creation in sevDesk for you.
  • Financial Audit Power: Reconciling receipts is tough. With list_vouchers and get_credit_note, your agent can pull up a physical receipt, compare it against a formal credit note, and tell you if they match—all from one prompt.
  • System Transparency: Need to know what accounts you're using? Call list_bank_accounts. You see exactly which bank nodes are active without having to manually check the core configuration settings.

Real-World Use Cases

01

A client needs a quick invoice summary.

The agent receives a query: "What's the net total on invoice #392911, and who is the attached client?" The system runs get_invoice to get the financials and then uses that data to reference the associated contact name. The result is an immediate, summarized answer for the user.

02

The team needs to reconcile a physical payment.

A voucher arrives showing 500 EUR. Instead of filing it manually and checking the ledger later, the agent uses list_vouchers to see recent entries and then runs get_credit_note against the voucher ID to confirm if that payment was already accounted for.

03

Setting up a new product line.

A sales manager doesn't know how to add a unique service. They ask the agent, "Add our new consulting package.". The agent uses create_part with the necessary details, making the item instantly available for use in future orders and invoices.

04

Auditing account setup.

The finance team wants to check if all required banking nodes are configured. They simply ask the agent to run list_bank_accounts. The system returns a list, confirming details like 'Deutsche Bank GmbH' and their current status.

The Tradeoffs

Trying to find one specific piece of data.

Writing five separate prompts: "Get contact 123.", "List invoices.", "What parts are available?", etc. This creates massive context overhead and requires manual stitching together of results.

Use the agent's conversational flow to chain calls. Start by calling list_contacts to identify a client, then pass that ID into an initial prompt asking for their latest invoice via get_invoice. The system handles the sequence.

Assuming data exists in memory.

Asking the agent about 'the last order' without providing any identifying number. The agent can't guess, and the query fails or returns nothing helpful.

Always start with a list tool to scope your search. Use list_orders first to get a range of IDs, then pass the target ID into get_order for specific details.

Manually comparing parts and orders.

Exporting an order list (CSV), opening the catalog (Excel), and cross-checking every part number manually to ensure pricing matches. This takes hours and is error-prone.

Instruct the agent to call get_order and then, within that single prompt, ask it to verify the price listed for each component against the current catalogue data using get_part. It does the comparison in one go.

When It Fits, When It Doesn't

Use this MCP server if your primary pain point is integrating accounting logic into your AI workflow. You need the agent to act like a virtual, knowledgeable bookkeeper who can perform multi-step transactions: find contacts (list_contacts), create items (create_part), and then generate billing documents (get_invoice).

Don't use this if you only need simple data visualization or document retrieval (e.g., reading a PDF attachment). For those tasks, a general file processing tool is better. Also, don't rely on it for complex regulatory advice; the tools provide raw data and state, but interpretation must come from your prompt. If you are building a system that needs to handle thousands of concurrent, high-velocity transactions per second (like a global payment processor), an event sourcing architecture might be required, which is beyond the scope of this current toolset.

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.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

How we secure it →

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This server provides 15 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.

Available Capabilities

create_contact create_part get_contact get_credit_note get_invoice get_order get_part list_accounting_types list_bank_accounts list_contacts list_credit_notes list_invoices list_orders list_parts list_vouchers

Manually tracking invoices and contacts eats up half your workday.

Right now, processing even one client request means logging into sevDesk. You pull up the customer's contact record; you check their invoice history to see if they paid last month; then you have to manually verify which parts were included in the original order against your current catalog prices. It’s a cycle of tabs, copy-pasting IDs, and opening three separate windows just to get one answer.

With this MCP server, that entire sequence is done by talking to your agent. You tell it what you need—for instance, "Tell me the full financial picture for Client X.". The agent calls `get_contact`, then iterates through all relevant invoices using `list_invoices` and `get_invoice`. It compiles everything into a single, clean response.

sevDesk MCP Server: Get real-time financial data from sevDesk.

Before this, updating or even reading core business records required deep knowledge of the sevDesk UI and API endpoints. You had to know if you needed a 'contact ID' or an 'order number,' and where those fields were located—a huge hurdle for any new user.

Now, your AI client handles the schema mapping. It knows that when you say "customer," it needs to call `list_contacts`. When you say "billing details," it calls `get_invoice`. The complexity of sevDesk's architecture is hidden from you; you just talk business.

Common Questions About sevDesk MCP

How do I find out what accounts are available for billing using the list_accounting_types tool? +

You run list_accounting_types to see every valid chart of account code. This provides a comprehensive list, ensuring your agent uses only approved accounting categories when generating new invoices or orders.

Can I use the get_invoice tool to see old payments? +

The get_invoice tool pulls specific invoice data, which includes payment status. For a full audit of past adjustments and refunds, you should also run list_credit_notes for context.

What is the difference between list_contacts and get_contact? +

list_contacts gives you a massive directory listing of every single client/supplier. Use get_contact when you already have an ID and need all the deep details on that one specific record.

Do I need to use list_parts before creating a new product with create_part? +

No, you don't. The create_part tool allows you to bypass listing and write the new catalog entry directly using your agent.

What happens if I use the get_invoice tool with an ID that doesn't exist? +

The AI client receives a structured error message instead of crashing. The agent reports the specific API failure (e.g., 'Invoice Not Found') so you can adjust your prompt or check the invoice number.

Are there limits if I run list_orders repeatedly? How do I get all records? +

The system implements rate limiting to prevent overload, but it supports pagination. Your agent automatically handles this by requesting subsequent pages until the full dataset of sales orders is gathered.

How should I manage my API token for secure connections across all tools? +

The connection requires a 32-character hexadecimal sevDesk API Token. Treat this credential like a password; never share it and ensure your AI client securely injects it into the environment.

Can I reference a newly created contact ID when getting an order using get_order? +

Yes, you can pass the new contact's unique identifier. This allows the agent to link the recently created client record directly to existing sales orders for comprehensive reporting.

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.

You might also like

Built & Managed by Vinkius 30s setup 15 tools

We've already built the connector for sevDesk. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 15 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.