Where do I find my Anvyl Team ID?

You can find your Team ID in the URL when you are logged into the Anvyl dashboard (e.g., `app.anvyl.com/teams/{TEAM_ID}/...`) or in your workspace settings.

Can I update the status of a production milestone via AI?

Yes, you can use the `confirm_milestone` tool to mark a milestone as complete or `delay_milestone` if production is behind schedule, providing a reason and a new expected date.

How do I track the shipping status of my orders?

Use the `list_logistics` tool with your Purchase Order ID. It will return all tracking records and shipping updates associated with that specific order.

Anvyl MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Anvyl
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 Anvyl 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="Anvyl Assistant",
            instructions=(
                "You help users interact with Anvyl. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Anvyl"
        )
        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 Anvyl MCP Server

The Anvyl MCP Server brings visibility and automation to your supply chain operations. By connecting your Anvyl account to your AI agent, you can seamlessly track production progress, manage parts and suppliers, and update critical milestones using natural language.

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

What you can do

Order Visibility — List all purchase orders and drill down into specific order details to check status and quantities.
Milestone Management — Track production and shipping milestones. Confirm completions or record delays directly from your chat.
Supplier Coordination — Quickly retrieve supplier information and part specifications stored in Anvyl.
Logistics Tracking — Access tracking records and logistics data for any purchase order to keep your team informed on delivery timelines.

The Anvyl 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 Anvyl to OpenAI Agents SDK via MCP

Follow these steps to integrate the Anvyl 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 Anvyl

Why Use OpenAI Agents SDK with the Anvyl MCP Server

OpenAI Agents SDK provides unique advantages when paired with Anvyl 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

Anvyl + OpenAI Agents SDK Use Cases

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

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

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

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

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

Anvyl MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Anvyl to OpenAI Agents SDK via MCP:

confirm_milestone

Confirm a milestone for a purchase order

delay_milestone

Delay a milestone for a purchase order

get_part

Get details for a specific part

get_purchase_order

Get details for a specific purchase order

get_supplier

Get details for a specific supplier

list_logistics

List tracking records for a purchase order

list_milestones

List milestones for a purchase order

list_parts

List parts in the Anvyl account

list_purchase_orders

List Anvyl purchase orders for the team

list_suppliers

List suppliers in the Anvyl account

Example Prompts for Anvyl in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Anvyl immediately.

"List all active purchase orders."

"Check the milestones for order PO-123."

"Delay milestone 'm_456' for order PO-789 by 1 week because of raw material shortage."

Troubleshooting Anvyl MCP Server with OpenAI Agents SDK

Common issues when connecting Anvyl 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.

Anvyl + OpenAI Agents SDK FAQ

Common questions about integrating Anvyl 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.