How to Use the Pennylane MCP in OpenAI Agents SDK

Connect your OpenAI Agents SDK to Pennylane to safely automate French tax compliance and invoice tracking with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pennylane MCP to OpenAI Agents SDK

Create your Vinkius account to connect Pennylane to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Pennylane with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Sync suppliers with OpenAI Agents SDK

The MCP Server exposes `list_supplier_invoices` to let your OpenAI Agents SDK pull French accounts payable data directly into your agent workflows. Your OpenAI agent inspects incoming bills, verifies supplier records using `get_supplier_details`, and matches them against your Pennylane ledger without manual intervention.

Safe customer onboarding via MCP Server

`create_customer` writes new client records straight to Pennylane while enforcing strict French VAT formatting through the OpenAI Agents SDK. Your OpenAI Agents SDK validates the tax registration data before committing the write, stopping bad data at the Pennylane API boundary.

Automate estimates with OpenAI Agents SDK

`list_estimates` pulls pending quotes so your OpenAI Agents SDK can trigger follow-ups or convert them to Pennylane sales. The OpenAI agent reads the exact line items using `get_estimate_details` and drafts the final invoice when the client signs off in Pennylane.

Setup guide

Set up Pennylane MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Pennylane tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Pennylane tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Pennylane tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Pennylane Agent",
            instructions="You have access to Pennylane tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Pennylane. 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 Pennylane 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 Pennylane MCP in OpenAI Agents SDK

Your agent auto-discovers all 13 tools instantly when you register the Pennylane HTTP endpoint. You pass the server streamable HTTP parameter during agent initialization, and the SDK maps the JSON schemas without manual coding.

Yes, you can control MCP tool access directly in your Python code. By configuring the OpenAI Agents SDK server streamable parameters, you filter out write tools like `create_product` to keep your agent in read-only mode.

The agent uses OpenAI's structured outputs to validate VAT fields before calling `get_customer_invoice_details`. This ensures the tax rates match the French Plan Comptable Général before any ledger write occurs.

The SDK handles connection drops gracefully via async context managers. If `list_customer_invoices` takes longer than 5 seconds, the agent catches the timeout exception and triggers a safe retry loop.

The MCP Server runs in an ephemeral V8 sandbox, meaning your invoices, customer names, and tax records are never stored on Vinkius. Your OpenAI Agents SDK communicates directly with Pennylane using one-time token authentication, keeping sensitive accounting logs isolated.

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