Can I check if an invoice has been paid through the agent?

Yes. The `list_accounting_invoices` tool allows your AI agent to see the current status of all invoices, including whether they are 'PAID', 'SAVED' (unpaid), or still in 'DRAFT' status.

How do I add a new client to my Wave account using chat?

You can use the `create_accounting_customer` tool. Just provide the customer's name and email address, and your agent will register them in your Wave business instantly.

Can I delete a draft invoice if I made a mistake?

Yes. The `delete_draft_invoice` tool allows you to permanently remove unfinalized draft invoices. Note that once an invoice is approved (SAVED) or paid, it cannot be deleted through this specific tool.

Wave Accounting MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Wave Accounting
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Wave Accounting through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Wave Accounting "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Wave Accounting?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Wave Accounting MCP Server

Connect your Wave Accounting account to any AI agent and manage your business finances through natural conversation.

Pydantic AI validates every Wave Accounting tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Customer Management — List all registered customers, create new profiles, and update contact information directly from your agent
Invoice Lifecycle — Create draft invoices, approve them for sending, and monitor their payment status (DRAFT, SAVED, PAID)
Deep Invoicing — Retrieve full details for any invoice, including line items, taxes, totals, and public payment URLs
Financial Auditing — Browse your customer base and billing activity to stay on top of your accounts receivable
Data Integrity — Safely delete unfinalized draft invoices or obsolete customer records through simple chat commands
Business Insights — Quickly find unique customer and invoice IDs required for complex accounting workflows

The Wave Accounting MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Wave Accounting to Pydantic AI via MCP

Follow these steps to integrate the Wave Accounting MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Wave Accounting with type-safe schemas

Why Use Pydantic AI with the Wave Accounting MCP Server

Pydantic AI provides unique advantages when paired with Wave Accounting through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Wave Accounting integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Wave Accounting connection logic from agent behavior for testable, maintainable code

Wave Accounting + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Wave Accounting MCP Server delivers measurable value.

Type-safe data pipelines: query Wave Accounting with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Wave Accounting tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Wave Accounting and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Wave Accounting responses and write comprehensive agent tests

Wave Accounting MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Wave Accounting to Pydantic AI via MCP:

approve_draft_invoice

Finalizes a draft invoice, moving it to an unpaid/saved status

create_accounting_customer

Provide name and email. Creates a new customer record in Wave

create_draft_invoice

Provide a customer ID and a JSON array of items. Creates a new draft invoice in Wave

delete_accounting_customer

This action is irreversible. Permanently deletes a customer record

delete_draft_invoice

Saved or paid invoices cannot be deleted via this endpoint. Permanently deletes an unfinalized draft invoice

get_customer_details

Retrieves details for a specific customer in Wave

get_invoice_details

Retrieves full details for a specific Wave invoice

list_accounting_customers

Lists customers registered in the Wave Accounting business

list_accounting_invoices

). Lists invoices issued by the Wave business

update_customer_profile

Provide the unique customer ID. Updates the profile of an existing customer

Example Prompts for Wave Accounting in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Wave Accounting immediately.

"List all my customers in Wave Accounting."

"Create a new customer for 'John Doe' with email 'john@example.com'."

"What is the status of my latest invoices?"

Troubleshooting Wave Accounting MCP Server with Pydantic AI

Common issues when connecting Wave Accounting to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Wave Accounting + Pydantic AI FAQ

Common questions about integrating Wave Accounting MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Wave Accounting MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.