How to Use the Assembled MCP in AutoGen

Q: How do AutoGen agents access the Assembled MCP Server?

Pull down the autogen-extmcp package. Wrap the Vinkius URL in StreamableHttpServerParams and feed it to the agent constructor.

Give your AutoGen multi-agent debates access to live Assembled workforce schedules.

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 AutoGen

Create your Vinkius account to connect Assembled to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate Staffing with the Assembled MCP Server

Multi-agent systems thrive on conflicting perspectives. One agent pulls expected volumes using `list_forecasts` while another checks the roster via `list_schedules`. They argue over whether the current shift can handle the projected spike. Getting tools into the conversation takes one line of code. You pass the Vinkius URL into `mcp_server_tools` and hand the list to your AssistantAgent. The bots immediately start querying the API to back up their arguments with actual numbers.

Negotiate Real-Time Queue Responses

Abstract discussions about support load are useless. A performance-focused agent runs `list_queues` to find out exactly where tickets are piling up. It demands action based on hard backlog data pulled via MCP. A separate manager agent counters by executing `list_agent_states`. It points out that half the team is currently stuck on long calls. The consensus they reach relies entirely on live floor conditions, not assumptions.

Cross-Reference Teams and Users

Reassigning work requires knowing who exists. The agents call `list_teams` to understand the departmental boundaries before proposing shift changes. They refuse to assign a billing specialist to a technical queue. Verifying specific headcount happens through `list_users`. The debate includes actual names and roles instead of generic placeholders. Your AutoGen system builds a highly specific staffing proposal grounded in your real directory.

Setup guide

Set up Assembled MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Assembled tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Assembled_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Assembled data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Assembled_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Assembled data")
    print(result.messages[-1].content)

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 AutoGen

Pull down the `autogen-ext[mcp]` package. Wrap the Vinkius URL in `StreamableHttpServerParams` and feed it to the agent constructor.

Concurrent reads work perfectly. The server handles requests from different agents participating in the same chat. They pull the data they need independently.

Only if you instruct them to check. They must actively call `list_queues` to read the current backlog metrics during their conversation.

The tool returns an error string to the chat. These agents read the failure message and typically decide to wait or try a different analytical approach.

Vinkius processes all requests inside an ephemeral V8 isolate. Live staffing patterns disappear from memory the second the HTTP response fires. The single MCP token keeps your authentication out of the agent prompts.

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