How to Use the Dixa MCP in AutoGen

Q: How do I register Dixa tools with AutoGen agents?

Use mcpservertools from autogen-extmcp to load the tools. Pass the resulting tool list to your AssistantAgent constructor to give them access.

Run multi-agent debates in AutoGen to resolve Dixa customer tickets and coordinate support teams automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dixa MCP to AutoGen

Create your Vinkius account to connect Dixa 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 Dixa with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate ticket resolution via agent debate

This MCP Server provides `resolve_conversation` so your AutoGen agents can close tickets after reaching a consensus. One agent reviews the conversation history while another verifies that the customer's issue is fully answered. Once both agents agree the issue is settled, they trigger the resolution tool. This prevents single-agent errors and ensures no customer ticket is closed prematurely.

Route tasks across Dixa teams using AutoGen

The MCP Server exposes `list_support_teams` to let your AutoGen agents debate which department should handle a complex ticket. A routing agent proposes a team, and a supervisor agent checks team availability. They use `assign_to_self` to claim the ticket once they agree on the best owner. This automates complex routing decisions through multi-agent negotiation.

Verify customer identity and history

Use `list_end_users` to let your agents verify a customer's identity before sharing account details. A security agent checks the user record while a support agent prepares the response. If the customer is new, they coordinate to call `create_customer_profile` and set up the profile. This collaborative workflow ensures customer records are clean and verified.

Setup guide

Set up Dixa 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 Dixa 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="Dixa_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use `mcp_server_tools` from `autogen-ext[mcp]` to load the tools. Pass the resulting tool list to your `AssistantAgent` constructor to give them access.

Yes. Agents can share the tool list, allowing one agent to run `list_conversations` while another agent calls `get_conversation_details` to analyze the thread.

One agent drafts the response based on customer history, and a supervisor agent reviews it. They then call `resolve_conversation` to close the ticket.

It supports both stdio and Streamable HTTP transports. AutoGen handles the schema conversion automatically using the built-in adapter.

Yes. All agent info and support team structures processed by the MCP Server are encrypted in transit. The Vinkius sandbox operates with zero-trust architecture, ensuring no operational data is leaked.

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