How to Use the Wave Accounting MCP in Pydantic AI

Q: Can I use Pydantic AI to create new customer records in Wave Accounting?

Yes. The createaccountingcustomer tool takes name and email as inputs. Because the output is validated, your agent gets clean, reliable data back every time.

Q: How do I check customer status using Pydantic AI with Wave Accounting?

You use the getcustomerdetails tool. The returned data, including the unique ID and profile details, will be validated against your specified Pydantic schema.

Ensure data integrity when building with Pydantic AI and Wave Accounting.

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 Pydantic AI

Create your Vinkius account to connect Wave Accounting to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Adding and Managing Customers

Need a new client in your database? Your agent calls `create_accounting_customer`, passing the customer name and email. Because you're using Pydantic AI, you know the data structure is correct before it hits Wave Accounting. The framework also supports reading existing user details. You can pull specific info with `get_customer_details` or list everyone registered by running `list_accounting_customers`. Don't forget to use `update_customer_profile` when a customer changes their contact information.

Handling Billing Documents

Creating an invoice starts with the agent calling `create_draft_invoice`, which requires both the customer ID and a defined array of line items. This ensures the billing data is correctly structured from the start. When it's time to finalize, the agent runs `approve_draft_invoice`. If you need to delete an unfinalized draft, use `delete_draft_invoice`; otherwise, saved or paid invoices are locked down.

Viewing Accounting History

The MCP Server provides tools for full accounting visibility. You can list every customer using `list_accounting_customers` or get a complete snapshot of any single user via `get_customer_details`. For billing history, start with `list_accounting_invoices`. Need the deep details on one specific bill? Run `get_invoice_details` to pull all the necessary data points for your Python agent.

Setup guide

Set up Wave Accounting MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "wave-accounting-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Wave Accounting tools.",
)

result = await agent.run("List recent Wave Accounting transactions")
print(result.output)

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 Pydantic AI

The core benefit is type safety. Every response from the MCP Server, like listing customers or invoices, must conform to a validated Pydantic model. If Wave Accounting sends bad data, your agent fails loudly—no silent corruption.

Yes. The `create_accounting_customer` tool takes name and email as inputs. Because the output is validated, your agent gets clean, reliable data back every time.

The system validates all incoming data structures for tools like `get_invoice_details` and `create_draft_invoice`. This guarantees that the billing information your agent uses is correct.

You use the `get_customer_details` tool. The returned data, including the unique ID and profile details, will be validated against your specified Pydantic schema.

The server primarily handles customer names, email addresses, and various invoice item details. These strings and IDs are the critical pieces of information validated by your agent.

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