Where do I find my Quaderno API Key and URL?

Log in to your Quaderno account. Your **API URL** is simply your domain up top in the browser bar (e.g., `https://mycompany.quadernoapp.com`). To get the **API Key**, navigate to **Settings** > **API Keys** (or Developers), and copy your private key. Do not share this key as it carries full access. Paste both credentials below.

Can it calculate exact taxes dynamically before a sale?

Yes! Use the `calculate_taxes` tool and just provide the AI with a country code, postal code, and base amount. Quaderno's world-class engine evaluates real-time location-based tax nuances (VAT, GST) and returns the exact fraction needed.

Can I draft custom test invoices natively in chat?

Absolutely. You can use `create_transaction`. Instruct your agent to format a JSON array with products and amounts, linking to a specific `contact_id`. The server submits this array to Quaderno and records the fully realized transaction safely.

Will deleting a contact via the AI remove them permanently?

Yes. The `delete_contact` operation relies heavily on standard destructive API instructions. Running this means the contact is gone entirely from the Quaderno dashboard. Always review deletion queries cautiously before approving execution.

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

Name: Quaderno
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 Quaderno through 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 Quaderno "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Quaderno?"
    )
    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 Quaderno MCP Server

Connect your Quaderno account to any AI agent and bring powerful tax compliance, invoicing, and customer management capabilities directly into your automated workflows.

Pydantic AI validates every Quaderno tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through 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

Tax Calculations on the Fly — Instantly determine the accurate sales tax, VAT, or GST based on the customer's region and amount before finalizing sales logic
Invoice Management — Search and retrieve generated invoices, audit billing records, and verify transactions perfectly formatted via intelligent prompts
Generate Transactions — Transact and issue invoices seamlessly by sending a simple JSON array of itemized products and line item prices
Full Contact CRM — Map your users fully by creating, modifying, retrieving, and safely deleting user contacts and billing profiles natively

The Quaderno 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 Quaderno to Pydantic AI via MCP

Follow these steps to integrate the Quaderno 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 Quaderno with type-safe schemas

Why Use Pydantic AI with the Quaderno MCP Server

Pydantic AI provides unique advantages when paired with Quaderno 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 Quaderno integration code

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

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

Quaderno + Pydantic AI Use Cases

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

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

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

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

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

Quaderno MCP Tools for Pydantic AI (10)

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

calculate_taxes

Calculates applicable taxes for a potential sale

create_contact

Specify email, first name, and last name. Creates a new contact in Quaderno

create_transaction

Provide the contact ID and a JSON array of items. Records a new transaction and issues an invoice

delete_contact

This action is irreversible. Deletes a contact from Quaderno

get_contact

Retrieves details for a specific contact

get_invoice

Retrieves details for a specific invoice

list_contacts

Lists all contacts (customers) in the Quaderno account

list_invoices

Lists all issued invoices

list_transactions

Lists all recorded transactions

update_contact

Provide a JSON payload with the changes. Updates an existing contact

Example Prompts for Quaderno in Pydantic AI

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

"Calculate the taxes for a $150 plan sold to a user in Berlin, Germany (Postal Code 10115)."

"Fetch the billing details and history for contact ID #9822."

"Update contact #9822 to change its first name to 'Acorn Group Inc'."

Troubleshooting Quaderno MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Quaderno + Pydantic AI FAQ

Common questions about integrating Quaderno 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 Quaderno MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.