How to Use the Simple Fatoora MCP in LangChain

Q: What if I need to change an item's price before billing with Simple Fatoora and LangChain?

First, run listitems to get the existing list. Then, use updateitem (if available) or manually structure the correct data for the next invoice call. The agent makes sure the updated item ID is used in the final billing step.

Q: Does Simple Fatoora and LangChain handle tax calculations correctly?

Yes, it does. Both createvatinvoice (B2B) and createsimplifiedinvoice (B2C) run the necessary automated tax logic, ensuring ZATCA compliance before generating the final invoice.

Q: Can I retrieve details for a specific customer using Simple Fatoora and LangChain?

Absolutely. You pass the client ID to getclient. This gives you all the necessary metadata—like tax IDs or billing addresses—before your agent uses that data to create any invoice.

Build multi-step invoicing agents with the LangChain MCP Client.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Simple Fatoora MCP to LangChain

Create your Vinkius account to connect Simple Fatoora 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 Simple Fatoora with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Agentic Invoicing Workflows for LangChain

Your agent decides the right sequence of calls. Need to check a client's status before billing? The agent runs `get_client` first, then uses that ID in a subsequent call to `create_vat_invoice`. It handles the logic flow itself. You can build complex pipelines where one tool's output dictates the next. For instance, an agent might run `list_items`, select three IDs, and then pass those three items directly into `create_simplified_invoice` for a single, structured call.

Manage Client Records using LangChain MCP Server

The framework lets you manage your customer list piece by piece. You can run `list_clients` to see everyone, and if you spot an error, the agent can execute `update_client` right away—no human intervention needed. Or, if a client is done with you, the agent handles it cleanly using `delete_client`. It’s all about making sure your multi-step process stays accurate from start to finish.

Automated Billing Chains with LangChain

The system manages both B2B and B2C invoicing. You simply tell the agent's objective. Does it need a simplified receipt, or does it require full ZATCA-compliant VAT billing? It knows which function to use: `create_simplified_invoice` or `create_vat_invoice`. This means you don't write branching logic; your ReAct agent figures out the right path through the MCP Server tools automatically. You just define the goal.

Setup guide

Set up Simple Fatoora 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 Simple Fatoora 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({
    "simple-fatoora-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 Simple Fatoora 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 Simple Fatoora. 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 Simple Fatoora 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 Simple Fatoora MCP in LangChain

Your LangChain agent can iterate through a list of client IDs found via `list_clients`. For each ID, it calls the appropriate invoicing tool—like `create_vat_invoice`—and collects all the resulting invoice data into one final output.

First, run `list_items` to get the existing list. Then, use `update_item` (if available) or manually structure the correct data for the next invoice call. The agent makes sure the updated item ID is used in the final billing step.

Yes, it does. Both `create_vat_invoice` (B2B) and `create_simplified_invoice` (B2C) run the necessary automated tax logic, ensuring ZATCA compliance before generating the final invoice.

Absolutely. You pass the client ID to `get_client`. This gives you all the necessary metadata—like tax IDs or billing addresses—before your agent uses that data to create any invoice.

The server handles sensitive business identifiers, including client names, VAT/Tax IDs, item descriptions, and calculated tax amounts. This is the type of financial transaction data you'll be working with.

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