How to Use the TaxBandits MCP in LangChain

Build multi-step tax pipelines for LangChain agents. Connect tools and observe every step.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect TaxBandits MCP to LangChain

Create your Vinkius account to connect TaxBandits 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 TaxBandits with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Check filing status with `get_submission_status`

Need to know if the IRS accepted that W-2 form? You call `get_submission_status`, and it spits out a definitive result. Your agent instantly knows if the filing passed or failed, so you can trigger follow-up actions right away. This is perfect for building complex chains. The status code becomes input for another tool—maybe telling your agent to alert the client or re-run data validation.

Create and manage business entities

Start by creating a new entity using `create_business`. You pass in all the necessary JSON data, and boom—the record is live. This initial output (the Business ID) can then be fed immediately into `get_business_details` to pull specific tax information. It’s about that flow: Use one tool's result as the trigger for the next. You build a full workflow where data moves automatically from creation to verification.

List and filter required tax forms

Want to see exactly what filings are due? Run `list_tax_forms` by passing your filters in JSON. This tells you which 1099s or ACA forms need attention, giving your agent a clean list of targets. Then, if you want the history on those forms, you use `list_transmissions`. Your LangChain agent decides whether to check current status or just look at past records based on what it knows.

Setup guide

Set up TaxBandits 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 TaxBandits 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({
    "taxbandits-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 TaxBandits 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 TaxBandits. 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 TaxBandits 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 TaxBandits MCP in LangChain

Your LangChain agent controls the flow. It decides which tool to call and in what sequence—for example, first checking `list_businesses`, then using that result to validate specific forms.

Yep. Since the MCP Server is stateless by default, you can reliably combine it with other APIs and databases in your chain without worrying about session drift or context loss.

The framework allows the agent to treat tool outputs as immediate inputs. If `get_business_details` fails, your chain can immediately pivot and try another approach, minimizing manual error risk.

You're dealing with core financial records: business entities, specific tax forms (like 1099), and filing submission statuses. Everything is structured JSON output.

The server handles core financial records and business entity data. Since it's an MCP Server, all interactions are managed via a single endpoint token for secure access.

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