How to Use the Simple Fatoora MCP in AutoGen

Q: If I need to check multiple invoices, how does Simple Fatoora and AutoGen help?

An agent can be assigned to run listinvoices, gather a set of IDs, and then sequentially prompt another agent to fetch details for each one via getinvoice. The results are compiled into a final report.

Automate consensus-driven billing with AutoGen MCP Server.

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Multi-Agent Invoice Consensus for AutoGen

You don't just run one tool; you make multiple agents debate the best path. One agent can handle client data validation by running `get_client`, while a second agent simultaneously handles tax calculation using `create_vat_invoice`. The system only finalizes the invoice when all agents agree on the structure and compliance. It’s built for decisions that require multiple perspectives.

Debatable Item Creation with AutoGen MCP Server

Need to create new items? Assign one agent to check item uniqueness via `list_items` and another agent to ensure the naming convention is correct. They argue until they agree on a single, valid name before the final `create_item` call runs. This simulates human review processes directly in your workflow.

Complex Billing Reconciliation with AutoGen

Use multiple agents to reconcile data. Agent A pulls all clients via `list_clients`. Agent B then takes that list and checks them against the required fields for `create_simplified_invoice`. They debate any missing mandatory information, ensuring you don't submit incomplete forms. This is ideal for high-stakes billing where accuracy means everything.

Setup guide

Set up Simple Fatoora 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 Simple Fatoora 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="Simple Fatoora_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Simple Fatoora 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="Simple Fatoora_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Simple Fatoora 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 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 AutoGen

You can assign a dedicated 'Tax Agent' whose sole job is to validate the rates before calling `create_vat_invoice`. This ensures the B2B invoice meets all complex ZATCA requirements through negotiation.

Yes. You can set up two distinct agents, one specialized in simple receipts (`create_simplified_invoice`) and another specialized for the full tax structure (`create_vat_invoice`). They work together based on the transaction type.

The agents can run through a validation loop. One agent checks `get_client` for completeness, while another runs `update_client` until consensus is reached on the correct, finalized record.

An agent can be assigned to run `list_invoices`, gather a set of IDs, and then sequentially prompt another agent to fetch details for each one via `get_invoice`. The results are compiled into a final report.

The process touches financial identifiers, including customer account details, item pricing structures, the specific tax rates applied (VAT), and the generated QR code payload. This is highly regulated billing information.

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