How to Use the Altoviz MCP in OpenAI Agents SDK

Q: How do I connect the Altoviz MCP Server to OpenAI Agents SDK?

Install openai-agents via pip. Create an MCPServerStreamableHttp instance with your Vinkius endpoint and pass it as mcpservers=server to the Agent constructor.

Q: Can OpenAI Agents SDK cache the Altoviz tool list?

Yes. Set cacheToolsList=True in your server parameters. This prevents the agent from re-fetching the tool schema every time it boots.

Q: Which Altoviz tools should I expose to a customer-facing OpenAI agent via MCP?

Keep it read-only and scoped. Expose getsalequotedetails and getproductdetails so the agent can answer pricing questions without seeing your internal receipts.

Build production-ready billing agents with OpenAI Agents SDK that query Altoviz invoices and customers safely.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Altoviz MCP to OpenAI Agents SDK

Create your Vinkius account to connect Altoviz to OpenAI Agents SDK 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 Altoviz with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trace Altoviz Invoices in OpenAI Agents SDK

Deployed agents need strict boundaries when touching financial records using the Altoviz MCP Server. You pass the endpoint to your agent constructor, and it auto-discovers `list_sale_invoices` without extra configuration. When a specialized billing agent pulls an invoice using `get_sale_invoice_details`, the entire execution path appears in your OpenAI dashboard. You see exactly which metadata the model read before deciding to draft a follow-up email.

Route Product Queries Between Agents

Multi-agent systems excel when you restrict their context to specific Altoviz tools. One agent handles support, and when a user asks about pricing, it hands off to a sales agent equipped with `list_products`. This sales agent pulls the current catalog via `get_product_details` and formulates a response. Built-in guardrails validate the action before the agent ever hits the Altoviz MCP endpoint, keeping your production system stable.

Automate Customer and Expense Audits

Manual expense tracking wastes time, so your OpenAI agent can run a scheduled job using `list_receipts` to pull recent Altoviz business expenses. It grabs the raw data directly from your accounting system. The agent then cross-references those expenses with specific clients using `list_customers`. If an anomaly appears, the system flags it for a human review instead of making unchecked assumptions.

Setup guide

Set up Altoviz 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 Altoviz tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Altoviz 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="Altoviz Agent",
            instructions="You have access to Altoviz 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 Altoviz. 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 Altoviz 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 Altoviz MCP in OpenAI Agents SDK

Install `openai-agents` via pip. Create an `MCPServerStreamableHttp` instance with your Vinkius endpoint and pass it as `mcp_servers=[server]` to the Agent constructor.

Yes. Set `cacheToolsList=True` in your server parameters. This prevents the agent from re-fetching the tool schema every time it boots.

It works flawlessly with handoffs. You can restrict the Altoviz tools to a specific finance agent, and your main routing agent will transfer control when a user asks for a quote.

Keep it read-only and scoped. Expose `get_sale_quote_details` and `get_product_details` so the agent can answer pricing questions without seeing your internal receipts.

Your customer metadata and sale invoices execute inside a V8 Isolate Sandbox. The Vinkius environment is ephemeral and destroys itself after the agent finishes the request, ensuring zero persistent access to your financial records.

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