How to Use the SimpleFatoora MCP in Pydantic AI

Q: What is the process for creating different invoice types with Pydantic AI?

You use specific tools like createvatinvoice for B2B tax documents or createsimplifiedpurchase for purchases. The framework forces you to provide all necessary, correctly typed parameters for each document.

Q: Can Pydantic AI handle multiple transaction types with SimpleFatoora?

Yes. Whether it's a standard purchase (createstandardpurchase) or a return note (createcreditnote), the framework enforces that all inputs and outputs conform to strict, predictable data schemas.

Q: How does SimpleFatoora handle product updates using Pydantic AI?

When calling updateproduct, the agent's payload must strictly match the expected types for every field. This prevents runtime errors and ensures that only valid data modifies your catalog.

Q: What data does SimpleFatoora touch when validating API keys? (Pydantic AI)

The validateapikey tool checks the format and active status of your token. It doesn't access or validate any customer, product, or invoice content.

Guarantee SimpleFatoora data accuracy with Pydantic AI type-safe validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect SimpleFatoora MCP to Pydantic AI

Create your Vinkius account to connect SimpleFatoora to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup SimpleFatoora with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Execute structured financial operations via the MCP Server.

The `create_vat_invoice` tool requires specific, validated inputs for tax rates and product SKUs. This means your agent cannot send a request with missing or wrongly typed data—it fails loudly. Similarly, creating a simplified sale using `create_simplified_invoice` demands precise payload structure. This strict validation is ideal when building mission-critical agents that absolutely cannot tolerate silent corruption of financial records.

Maintain clean and accurate customer data.

When you run `update_customer`, Pydantic AI ensures the payload matches the expected schema; if an address field is wrong, the agent fails immediately. You can list users with `list_customers` and get detailed profiles using `get_customer`. The whole process adheres to strong typing. Even when deleting a customer record with `delete_customer`, the validation framework confirms the operation parameters are correct.

Manage product records reliably for SimpleFatoora.

If you create an item using `create_product`, Pydantic AI validates every field—from descriptions to tax categories. When retrieving data with `get_product` or listing items via `list_products`, the output schema is guaranteed to be correct. This focus on correctness means your agent always receives predictable, reliable Python objects that you can trust in downstream code.

Setup guide

Set up SimpleFatoora MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "simplefatoora-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to SimpleFatoora tools.",
)

result = await agent.run("List recent SimpleFatoora transactions")
print(result.output)

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 SimpleFatoora. 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 SimpleFatoora 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 SimpleFatoora MCP in Pydantic AI

Pydantic AI validates every single MCP response against defined models at runtime. If the API sends back unexpected fields or types, your agent fails immediately and throws a clear validation error.

You use specific tools like `create_vat_invoice` for B2B tax documents or `create_simplified_purchase` for purchases. The framework forces you to provide all necessary, correctly typed parameters for each document.

Yes. Whether it's a standard purchase (`create_standard_purchase`) or a return note (`create_credit_note`), the framework enforces that all inputs and outputs conform to strict, predictable data schemas.

When calling `update_product`, the agent's payload must strictly match the expected types for every field. This prevents runtime errors and ensures that only valid data modifies your catalog.

The `validate_api_key` tool checks the format and active status of your token. It doesn't access or validate any customer, product, or invoice content.

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