How to Use the Presumed Profit Tax Calculator MCP in LangChain

Q: Can LangChain agents decide which tax tool to use?

Yes. You pass the tools to createagent, and the LLM determines the execution order based on the financial data provided.

Build automated corporate tax pipelines in LangChain by chaining presumed profit calculations directly into your ReAct agents.

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 LangChain

Create your Vinkius account to connect Presumed Profit Tax Calculator 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 Presumed Profit Tax Calculator with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain tax base logic in LangChain

Your ReAct agents need structured financial inputs before they figure out tax liabilities. This MCP feeds exact margin data straight into your agent's context window. Calling `get_taxable_base` turns raw gross revenue and activity types into a standardized figure. LangChain then passes that output to the next node in your graph without manual data wrangling.

Automate CIT and SCLL steps

Complex Brazilian tax rules require precise sequencing. You build the pipeline; the agent decides when to trigger the 15% standard rate or the 10% surtax based on intermediate results. When the graph executes, `calculate_cit_breakdown` handles the corporate income tax splits. Right after that, `calculate_scll_liability` runs the 9% social contribution math, fully observable in LangSmith.

Output consolidated LangChain reports

Single-step calculations mean nothing if you cannot present the final numbers to a user or database. Your multi-step reasoning pipeline ends with a clean aggregation. The agent triggers `generate_tax_summary_report` to pull all previous steps into one consolidated liability sheet. You drop that final payload into a vector store or return it directly to the user interface.

Setup guide

Set up Presumed Profit Tax Calculator 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 Presumed Profit Tax Calculator 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({
    "presumed-profit-tax-calculator-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 Presumed Profit Tax Calculator 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 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 LangChain

Run pip install langchain-mcp-adapters langgraph. Then initialize a MultiServerMCPClient pointing to the Vinkius endpoint.

Yes. You pass the tools to create_agent, and the LLM determines the execution order based on the financial data provided.

Every API call logs directly into LangSmith. You track token usage, latency, and exact tool inputs for the tax calculations.

You can aggregate this MCP alongside database tools in the same chain. The agent pulls revenue from your SQL database and passes it to the tax calculator.

The system processes gross revenue and sector types strictly in memory. We do not store your corporate financial inputs on Vinkius infrastructure.

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