How to Use the Anvyl MCP in OpenAI Agents SDK

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

Install openai-agents, then instantiate MCPServerStreamableHttp using the Vinkius endpoint. Pass the server instance inside the mcpservers list when initializing your agent.

Q: How does caching work with Anvyl and OpenAI Agents SDK?

Set cacheToolsList=True in your connection parameters. This prevents the SDK from refetching the tool definitions on every single agent loop, speeding up supply chain queries.

Q: Does the OpenAI Agents SDK support async execution for this MCP Server?

It does. You should use the async with context manager block to handle the connection, ensuring your server calls don't block your main application thread.

Run safe, production-grade supply chain agents with OpenAI Agents SDK and the Anvyl MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Anvyl MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe PO updates with OpenAI Agents SDK

Your OpenAI agent can safely modify shipping dates and confirm completions on your supply chain pipeline. By exposing `confirm_milestone` and `delay_milestone`, your production system updates order timelines without manual intervention. Because OpenAI Agents SDK supports strict tracing, you can monitor every time an agent shifts a milestone. This keeps your logistics pipeline accountable and prevents runaway automated schedule changes.

Multi-agent handoffs for supply chain audits

Build a specialized supplier auditor agent that hands off to a logistics coordinator agent. One agent uses `list_suppliers` and `get_supplier` to check vendor health, then hands the context over to another agent to track active shipments. This MCP Server partition lets you assign distinct system instructions to each agent. Your supplier vetting agent won't accidentally trigger shipping changes because it only accesses the specific lookup tools it needs.

Real-time inventory and logistics tracking

Keep your customer service agents updated on transit issues. The agent calls `list_logistics` and `get_purchase_order` to find out exactly where parts are stuck before replying to a user query. Running this inside an async context manager with the OpenAI Agents SDK ensures low latency. The agent quickly pulls part details using `get_part` to give your team immediate, accurate answers.

Setup guide

Set up Anvyl 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 Anvyl tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents`, then instantiate `MCPServerStreamableHttp` using the Vinkius endpoint. Pass the server instance inside the `mcp_servers` list when initializing your agent.

Yes. You can define specific system guardrails in your OpenAI Agent configuration to restrict access to tools like `delay_milestone` while keeping lookup tools active.

Set `cacheToolsList=True` in your connection parameters. This prevents the SDK from refetching the tool definitions on every single agent loop, speeding up supply chain queries.

It does. You should use the `async with` context manager block to handle the connection, ensuring your server calls don't block your main application thread.

Vinkius hosts the server in a zero-trust, ephemeral V8 isolate. Your purchase order details and milestone dates are never stored on the server, keeping your supply chain records private.

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