How to Use the Presumed Profit Tax Calculator MCP in Pydantic AI

Build type-safe corporate tax pipelines with Pydantic AI to validate every CIT and SCLL calculation at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Presumed Profit Tax Calculator MCP to Pydantic AI

Create your Vinkius account to connect Presumed Profit Tax Calculator 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 Presumed Profit Tax Calculator with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-Safe Tax Base Calculations

This MCP guarantees that your tax base calculations conform to strict schemas before your code ever runs. By calling `get_taxable_base`, your agent calculates the presumptive base from your gross revenue, validating the input and output types instantly. If the calculation engine returns unexpected data, the framework raises a validation error immediately. This prevents silent failures and ensures your financial pipelines only process mathematically sound data.

Validate CIT and SCLL Liabilities at Runtime

Ensure your corporate income tax and social contribution calculations are perfectly typed. Your agent calls `calculate_cit_breakdown` to compute corporate income tax and surtaxes, and uses `calculate_scll_liability` to calculate social contribution liabilities. Every field in the returned payload is validated against strict Pydantic models. You never have to worry about missing fields or corrupted floats when writing these values to your database.

Generate Validated MCP Server Tax Summaries

Compile your entire tax liability into a single, fully typed report. Your agent calls `generate_tax_summary_report` to aggregate CIT and SCLL details into a structured summary. This ensures that your consolidated tax reports are always structurally sound. It makes it safe to feed the output directly into downstream automated billing or accounting systems.

Setup guide

Set up Presumed Profit Tax Calculator 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": {
        "presumed-profit-tax-calculator-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Presumed Profit Tax Calculator 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 Presumed Profit Tax Calculator. 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 Presumed Profit Tax Calculator 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 Presumed Profit Tax Calculator MCP in Pydantic AI

Import the toolset class and initialize it with your hosted endpoint URL. Pass the toolset directly to your agent instance to expose the calculations to your model.

Yes. The framework natively supports asynchronous tool execution, allowing your agent to run multiple tax calculations concurrently without blocking your application.

The framework validates all tool outputs against strict schemas. If any calculation returns unexpected types or missing fields, a runtime validation error is raised immediately, stopping the pipeline before bad data spreads.

Yes. The tool integration is model-agnostic, meaning you can connect these tax calculation tools to any supported LLM provider or local model running on your infrastructure.

No financial data, revenue figures, or calculated tax liabilities are stored or logged by the calculation engine. All data transmission occurs over encrypted channels, and inputs are processed purely in-memory.

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