How to Use the sevDesk MCP in LlamaIndex

Q: How do I search for past invoices using sevDesk and LlamaIndex?

First, call listinvoices to get the raw data. Then, index that output into your vector store. You can query the index later with natural language questions like, 'Show me all large invoices from last year.'

Q: Does sevDesk and LlamaIndex help track supplier details?

Yes. After running listcontacts, you index the resulting contact records. You can then query for specific suppliers' payment terms or roles without needing to know their exact ID.

Q: Can I combine sales orders and parts data using sevDesk and LlamaIndex?

You absolutely can. By indexing the results of both listorders and listparts, you create a searchable knowledge base that connects these two domains, letting your agent answer questions like, 'What was ordered in SO 123 that corresponds to Part ABC?'

Q: How do I check if an account exists in sevDesk and LlamaIndex?

You can run listaccounts to get the full list, then index it. Later, you'll query the knowledge base asking, 'Does a bank account for XYZ exist?' The answer is grounded in your indexed data.

Ground your AI decisions in actual sevDesk data using LlamaIndex and its vector store indexing.

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 LlamaIndex

Create your Vinkius account to connect sevDesk to LlamaIndex — 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Query Historical Financial Records

Instead of just calling `list_invoices`, you index the output of that tool. This means you can query your knowledge base like, 'What were all invoices over $5k for Acme Corp last quarter?' and get answers grounded in real data. The LlamaIndex framework turns raw API outputs into a searchable index. You build RAG applications where past financial summaries are available for semantic search.

Track Contact History with Context

Need to know why you sent that credit note? Indexing the results of `get_credit_note` lets your agent answer, 'Why did we issue a credit note to John Doe last month?' It doesn't just fetch data; it explains it based on indexed details. The process is simple: run `list_contacts`, index the resulting text snippets, and then query for specific context.

Analyze Parts and Services by Description

Traditional searches fail when you don't know the part number. Indexing `list_parts` allows your agent to answer natural language queries like, 'Which parts are used for Model X that cost less than $100?' You combine live API data with document context in a unified index. This approach is powerful because it combines catalog data (`get_part`) with unstructured knowledge.

Setup guide

Set up sevDesk MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all sevDesk MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to sevDesk tools.",
)
response = await agent.run("List recent sevDesk data")

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 LlamaIndex

First, call `list_invoices` to get the raw data. Then, index that output into your vector store. You can query the index later with natural language questions like, 'Show me all large invoices from last year.'

Yes. After running `list_contacts`, you index the resulting contact records. You can then query for specific suppliers' payment terms or roles without needing to know their exact ID.

You absolutely can. By indexing the results of both `list_orders` and `list_parts`, you create a searchable knowledge base that connects these two domains, letting your agent answer questions like, 'What was ordered in SO #123 that corresponds to Part ABC?'

This server touches contact information (contact data). By indexing this, you're creating a searchable history of customer interactions. Make sure your vector store is secure.

You can run `list_accounts` to get the full list, then index it. Later, you'll query the knowledge base asking, 'Does a bank account for XYZ exist?' The answer is grounded in your indexed data.

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