How to Use the Wave Accounting MCP in LangChain

Q: How can I check customer status using Wave Accounting and LangChain?

Your agent uses getcustomerdetails to pull the latest profile information for any contact. This lets you verify addresses or check if an account is flagged before proceeding with other tasks.

Q: What happens if I need to correct an old record using Wave Accounting and LangChain?

You can use a combination of tools. First, run getcustomerdetails to see what's wrong, then call updatecustomerprofile. The agent handles the logic for when those calls are necessary.

Q: Does this MCP Server support deleting data from Wave Accounting and LangChain?

Yes. You can use tools like deleteaccountingcustomer or deletedraftinvoice. Be careful, though—these actions are permanent and irreversible.

Build complex, multi-step reasoning pipelines for Wave Accounting actions with LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Wave Accounting MCP to LangChain

Create your Vinkius account to connect Wave Accounting 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 Wave Accounting with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Complex customer lifecycle management in LangChain

You can build a chain that first finds a contact using `get_customer_details`, then updates their billing address via `update_customer_profile`. This allows your agent to manage the full customer journey before moving on. Agents use these tools to decide which action comes next. For example, if an invoice is overdue, the chain might call `list_accounting_customers` first to confirm contact status before attempting a reminder.

Invoice generation and approval workflows with LangChain

Need to send out invoices? Your agent handles that. It can create a draft using `create_draft_invoice`, then wait for confirmation from another step in the chain before calling `approve_draft_invoice`. This ensures nobody approves an invoice by accident. The full control means you can also clean up mistakes by invoking `delete_draft_invoice` if the original transaction needs to be scrapped.

Full Wave Accounting data retrieval with LangChain

The MCP Server exposes tools that let your agent read everything it needs. You can list all contacts using `list_accounting_customers`, or retrieve a specific invoice history by running `list_accounting_invoices`. This gives the agent the full context required to make smart decisions. Accessing data is simple: calling `get_invoice_details` pulls every piece of information about one specific bill, keeping your multi-step process grounded in facts.

Setup guide

Set up Wave Accounting 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 Wave Accounting 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({
    "wave-accounting-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 Wave Accounting 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 Wave Accounting. 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 Wave Accounting 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 Wave Accounting MCP in LangChain

Your agent uses `get_customer_details` to pull the latest profile information for any contact. This lets you verify addresses or check if an account is flagged before proceeding with other tasks.

Absolutely. You'll set up a chain where the agent first calls `create_draft_invoice` with item details, then waits for approval before finalizing it with `approve_draft_invoice`. This handles the whole workflow automatically.

You can use a combination of tools. First, run `get_customer_details` to see what's wrong, then call `update_customer_profile`. The agent handles the logic for when those calls are necessary.

Yes. You can use tools like `delete_accounting_customer` or `delete_draft_invoice`. Be careful, though—these actions are permanent and irreversible.

The client supports multi-server aggregation. You can combine this MCP Server's tools with others in a single chain to manage your business across different platforms.

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