How to Use the ISS Calculator MCP in LangChain

Build automated Brazilian tax reasoning MCP pipelines with LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ISS Calculator MCP to LangChain

Create your Vinkius account to connect ISS 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 ISS Calculator with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

LangChain agents fetch local ISS rates

The `get_applicable_rate` tool connects your agent directly to municipal tax tables. You pass the city code and service type to get the exact percentage required for invoicing. This setup replaces manual spreadsheet checks with an automated step in your chain. ReAct agents use the output to decide if they need to query a different municipality based on where the work happened.

Determine tax responsibility instantly

Your pipeline calls `check_withholding_status` to figure out if the service provider or the buyer must remit the tax. Brazilian law forces buyers to withhold ISS for specific services like construction or cleaning. Agents log this decision via LangSmith tracing. You see exactly why the chain decided a specific invoice needed withholding before it hits your accounting database.

Execute final MCP math operations

Once the agent knows the rate and rules, it triggers `calculate_tax_liability` to compute the actual currency amount owed. It handles the base calculation minus any legal deductions. The resulting figure flows directly into your billing integrations. You avoid math errors because the agent relies on the structured API response instead of doing arithmetic in the prompt.

Setup guide

Set up ISS 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 ISS 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({
    "iss-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 ISS 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 ISS 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.