How to Use the Luma MCP in AutoGen

Build consensus-driven event workflows by letting AutoGen agents negotiate Luma tool calls.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Luma MCP to AutoGen

Create your Vinkius account to connect Luma 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 Luma with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Negotiate event logistics between agents

In an AutoGen setup, one agent can propose a new gathering using `create_event` while another checks the organization calendar for conflicts. They debate the best time until they agree. This prevents scheduling errors. Once they reach a consensus, the chosen agent executes the final call to the API.

Verify guest lists via agent debate

You can have a security agent flag potential issues in a guest list retrieved by `list_event_guests`. A coordinator agent then processes these flags to decide which guests to keep. This adds a layer of scrutiny to your invite process. The system ensures that only the right people are added to your event via `add_guests_to_event`.

Monitor subscriber growth through collaboration

Multiple agents analyze your `list_calendar_subscribers` output to spot trends. They discuss these findings and determine if you should increase your marketing efforts for upcoming events. This collaborative approach leads to better decision making. The agents share the data from the MCP Server to ensure everyone is working from the same source of truth.

Setup guide

Set up Luma 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 Luma 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="Luma_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Luma 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="Luma_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Luma 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 Luma. 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 Luma 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 Luma MCP in AutoGen

You provide the tool list to the AssistantAgent constructor. The MCP adapter handles the schema conversion, allowing every agent in your conversation to invoke the tools.

Absolutely. You can assign specific tools to specific agents, so one agent handles creation while another manages the guest lists and reporting.

The agents debate the instructions. If one agent tries to create an event at a bad time, another agent can use `list_events` to show the conflict and force a revision.

Yes, the MCP server supports streaming HTTP, which ensures that your agents get the tool results as quickly as possible during their deliberations.

The tools process guest data only within the specific agent's context. Because you control the agents, you decide which data is shared between them during their negotiation.

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