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 OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Quaderno
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Quaderno through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

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 agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Quaderno Assistant",
            instructions=(
                "You help users interact with Quaderno. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Quaderno"
        )
        print(result.final_output)

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.

The OpenAI Agents SDK auto-discovers all 10 tools from Quaderno through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Quaderno, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

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 OpenAI Agents SDK 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 OpenAI Agents SDK via MCP

Follow these steps to integrate the Quaderno MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Quaderno

Why Use OpenAI Agents SDK with the Quaderno MCP Server

OpenAI Agents SDK provides unique advantages when paired with Quaderno through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Quaderno + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Quaderno MCP Server delivers measurable value.

Automated workflows: build agents that query Quaderno, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Quaderno, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Quaderno tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Quaderno to resolve tickets, look up records, and update statuses without human intervention

Quaderno MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Quaderno to OpenAI Agents SDK 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 OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK 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 OpenAI Agents SDK

Common issues when connecting Quaderno to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Quaderno + OpenAI Agents SDK FAQ

Common questions about integrating Quaderno MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.