How to Use the Evoliz MCP in LangChain

Q: Can LangChain handle French tax compliance rules automatically with Evoliz?

Yes, by chaining tool calls. Your agent can run getinvoice to verify compliant tax rates before drafting new documents, ensuring your LangChain workflows respect French anti-fraud invoicing laws.

Run multi-step French invoicing and billing workflows in LangChain using your live Evoliz accounting data through this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Evoliz MCP to LangChain

Create your Vinkius account to connect Evoliz to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Evoliz with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Evoliz MCP Server tools for multi-step billing

Stop manually copying data between tools. Your LangChain agent can now fetch a quote via `get_quote`, parse the details, and immediately trigger `create_client` using the extracted customer information. It links operations directly, passing outputs as inputs to the next chain link. This setup handles the entire French accounting pipeline without human intervention. The agent checks `list_quotes` to find open deals, drafts the invoice, and updates your ledger while keeping every step in your existing LangChain run.

Trace tax compliance steps with LangSmith

When dealing with strict French anti-fraud laws, you need to know exactly why an invoice was generated or modified. Running `get_invoice` or `list_invoices` inside a LangChain runnable via this MCP Server gives you full LangSmith observability. You can audit the precise inputs, token costs, and tool responses for every single tax document. If a client creation fails during `create_client`, you won't have to guess what went wrong. The trace shows the raw payload sent to the API, making it simple to debug tax ID formats or missing address fields before they hit your official French accounting records.

Direct agent decisions on catalog items

Let your LLM decide how to handle inventory based on real-time data. The agent runs `list_articles` to check your current catalog, matches it against incoming customer requests, and uses `get_article` to pull exact pricing and tax rates before generating a proposal. You don't write complex routing logic for this. The LangChain agent evaluates the user's prompt, selects the correct tool from the MCP Server, and runs the query. It keeps your stock and pricing synchronized with zero hardcoded scripts.

Setup guide

Set up Evoliz 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 Evoliz 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({
    "evoliz-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 Evoliz 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 Evoliz. 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 Evoliz 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 Evoliz MCP in LangChain

You install the adapter via pip install langchain-mcp-adapters and instantiate the client. Pass the tools retrieved from the Vinkius endpoint directly into your agent constructor to let it run operations like `list_invoices`.

Yes, by chaining tool calls. Your agent can run `get_invoice` to verify compliant tax rates before drafting new documents, ensuring your LangChain workflows respect French anti-fraud invoicing laws.

Use the built-in pagination parameters. Instead of dumping your entire database into the prompt, have your LangChain agent request smaller chunks or search for specific targets using `get_client`.

Absolutely. You can combine this server with database or email tools. The agent can pull a record using `get_quote` and immediately write those details to a local database using your other LangChain integrations.

Your sensitive client details, VAT numbers, and invoice amounts never touch third-party databases. Vinkius runs the server in an isolated sandbox, and your LangChain client communicates directly through a single secure endpoint token.

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