How to Use the Humanitix MCP in AutoGen

Q: Can AutoGen agents debate inventory allocation using Humanitix data?

Yes, your agents can call listinventory and listtickets to compare sales across different categories. They will discuss and resolve how to allocate remaining seats.

Q: Can I use the Humanitix MCP tools with multiple AutoGen agents simultaneously?

Yes. You register the tools like listcampaigns and listevents with the agent group manager, allowing any agent in the conversation to invoke them when needed.

Let your AutoGen agents debate ticket pricing and coordinate event check-ins using real-time Humanitix data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Humanitix MCP to AutoGen

Create your Vinkius account to connect Humanitix 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 Humanitix with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate Event Logistics via Multi-Agent Debate

We feed your agent conversation threads live venue and host details using `list_venues` and `list_hosts`. A logistics agent queries the venue capacity, while a marketing agent reviews past campaign performance to negotiate the best layout. They debate the options and converge on an optimal setup. The conversation uses `get_event` to verify dates and times before finalizing any plans. This ensures that no scheduling conflicts occur during the multi-agent planning phase.

Audit Sales with the AutoGen MCP Server

This MCP Server provides `list_tickets` and `list_inventory` so your agents can monitor sales velocity. A finance agent checks the revenue, while an inventory agent flags ticket tiers that are running low. They negotiate whether to release more tickets or adjust pricing. Because the schema conversion is handled automatically, you don't write custom parsers for the ticket payloads. The agents read the structured JSON and immediately start their discussion.

Resolve Order Discrepancies Automatically

Your agent uses `list_orders` and `list_attendees` to investigate customer support tickets. When a discrepancy is found, a customer service agent retrieves the order details, while a compliance agent checks the event policies. They deliberate to decide if a manual override is required. This consensus-driven approach ensures that refunds or ticket changes are double-checked by multiple perspectives. The final decision is logged using `get_me` to record the user context.

Setup guide

Set up Humanitix 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 Humanitix 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="Humanitix_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use the autogen-ext package to initialize the MCP tool adapter. Pass the server URL to the streamable HTTP parameters, then add the retrieved tools to your AssistantAgent.

Yes, your agents can call `list_inventory` and `list_tickets` to compare sales across different categories. They will discuss and resolve how to allocate remaining seats.

The agents handle rate limits by coordinating their API calls. If `list_orders` returns a rate limit error, the executing agent communicates this to the other agents to pause the debate.

Yes. You register the tools like `list_campaigns` and `list_events` with the agent group manager, allowing any agent in the conversation to invoke them when needed.

The server transmits order details and attendee emails directly over an encrypted, ephemeral connection. No customer records or event details are cached or stored on the hosting platform.

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