How to Use the Assembled MCP in OpenAI Agents SDK

Q: Which tool verifies my Assembled connection?

Run getaccountcheck to confirm your credentials are valid. Doing this early prevents failed API calls later in your agent's execution loop.

Q: How does the agent know which Assembled team handles a ticket?

It calls listteams to read your current routing structure. You can enforce strict handoffs between agents based on these team definitions.

Build production workforce agents by connecting Assembled to the OpenAI Agents SDK for real-time schedule tracking.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Assembled MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track real-time support capacity

Your routing agent needs to know who is actually working before assigning tickets. Calling `list_agent_states` returns the exact status of every rep on the floor. Handoffs between specialized agents happen instantly when volume spikes. You can cross-reference this with `list_schedules` to catch discrepancies. Built-in guardrails validate the agent's logic before it reassigns any work. That keeps your production environment stable.

Monitor queues and forecasts via MCP

Predictable support requires accurate data. Your agent pulls expected contact volume using `list_forecasts` directly through this MCP connection. It then checks `list_queues` to see where the current backlog lives. Tracing via the OpenAI dashboard shows exactly how your agent weighed the forecast against the current queue. You get full visibility into every decision. No guessing why the agent escalated a specific channel.

Map your organizational structure

Managing a massive support org gets messy fast. Running `list_teams` gives your agent the exact hierarchy it needs to route escalations. It pairs perfectly with `list_users` to identify specific shift managers. Setup is simple with the OpenAI Agents SDK. Just pass the MCP Server to your Agent constructor and set cacheToolsList to true. The framework handles tool discovery automatically.

Setup guide

Set up Assembled 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 Assembled tools at runtime.
3

Create your Agent

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

Run the agent

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

Use the MCPServerStreamableHttp class. Pass the Vinkius endpoint URL and include it in your agent's mcp_servers list. Tool discovery happens on startup.

Yes. Set cacheToolsList to true when configuring the MCP Server connection. This speeds up initialization for agents that restart frequently.

Run `get_account_check` to confirm your credentials are valid. Doing this early prevents failed API calls later in your agent's execution loop.

It calls `list_teams` to read your current routing structure. You can enforce strict handoffs between agents based on these team definitions.

Your agent schedule and queue data stays isolated. The Vinkius V8 sandbox processes the request ephemerally and destroys the environment immediately after returning the JSON payload. We never store your workforce metrics.

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