How to Use the Axonaut MCP in OpenAI Agents SDK

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

Install openai-agents via pip. Create an MCPServerStreamableHttp instance using your Vinkius URL and pass it to the mcpservers array in your Agent constructor.

Q: Can OpenAI Agents SDK create new Axonaut records?

Yes, the agent can call createtask to add items directly to your workspace. It cannot create new invoices or companies, as those tools are read-only in this specific server.

Q: How do I verify my Axonaut connection in OpenAI Agents SDK?

Call the getaccountcheck tool right after initialization. This confirms your Vinkius token is valid and returns the current user profile.

Build production ERP agents with OpenAI Agents SDK that read Axonaut invoices and create tasks safely.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Axonaut MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

OpenAI Agents SDK task automation

Your deployment needs strict boundaries when touching company data. By plugging this MCP Server into your agent setup, you give it direct access to `create_task` and `list_tasks` without writing custom API wrappers. Handoffs work perfectly here. You might have one specialized agent scanning emails to trigger `list_contacts`, while another agent takes that output and generates follow-up assignments. Built-in guardrails validate every single parameter before hitting the Axonaut endpoint.

Financial data retrieval

Fetching pricing history usually means digging through terrible UI screens. Now your Python code can run `list_invoices` and `list_expenses` straight from the script. Auto-discovery handles the heavy lifting. You pass the server into your Agent constructor, and it instantly knows how to pull records using `list_quotations`. Tracing in the dashboard shows exactly which records the model requested.

Cross-referencing CRM records

Context matters when dealing with customer accounts. Your system can hit `list_companies` to grab a client list, then immediately call `get_company` for specific details. That means no more guessing if a contact belongs to an active project. The agent checks `list_projects` against `list_contacts` and flags discrepancies. Set `cacheToolsList=True` during initialization to keep these rapid-fire lookups fast.

Setup guide

Set up Axonaut 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 Axonaut tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` via pip. Create an `MCPServerStreamableHttp` instance using your Vinkius URL and pass it to the `mcp_servers` array in your Agent constructor.

Yes, the agent can call `create_task` to add items directly to your workspace. It cannot create new invoices or companies, as those tools are read-only in this specific server.

It works exactly as expected. One agent can pull data using `list_orders` and hand that context off to a secondary agent responsible for reporting.

Call the `get_account_check` tool right after initialization. This confirms your Vinkius token is valid and returns the current user profile.

Vinkius isolates every session in a V8 sandbox. When your script pulls billing totals or expense reports, that data flows through an ephemeral environment that vanishes the second the connection drops. Nothing is cached on our end.

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