How to Use the Avochato MCP in AutoGen

Q: Can I set up an AutoGen agent to manage Avochato support tickets?

Yes. You can create a 'SupportAgent' that uses listtickets to find work, and an 'EngineerAgent' that it can talk to. They can collaborate on a solution before the support agent uses updateticket.

Q: What's an example of an agent debate using Avochato tools?

A 'Sales' agent uses createcontact for a new lead. A 'Data' agent then uses listcontacts and flags it as a potential duplicate. They debate until the Sales agent uses updatecontact to merge the info.

Have multiple AutoGen agents debate the best way to respond to customers and manage Avochato tickets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Avochato MCP to AutoGen

Create your Vinkius account to connect Avochato 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 Avochato with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Customer Support

This isn't about one agent following a script. With AutoGen, you set up a team of agents that talk to each other. A 'Support' agent can use `list_tickets` to flag an urgent issue, while a 'QA' agent uses `list_messages` to review the conversation and check for details. They debate the next move. The Support agent might propose a reply, but a 'Manager' agent could use `get_contact` to see the customer's history and suggest escalating instead. The final action, like `update_ticket`, is a consensus decision reached through conversation.

Debate-Driven Messaging with AutoGen

Give your agents the Avochato tools they need to build a case. An 'Outreach' agent can draft a marketing text, but a 'Compliance' agent can halt the process, use `get_contact` to verify opt-in status, and only then approve the `send_message` call. This back-and-forth, with each agent using tool calls as evidence, results in better decisions. You're not just automating actions; you're automating deliberation. It's a system that thinks before it texts.

Automated Contact Vetting

Use an agent conversation to keep your contact list clean. One agent can be responsible for adding new leads using `create_contact`. A second 'Auditor' agent can then periodically use `list_contacts` to find unverified entries and cross-reference them. This conversational workflow means you don't just blindly add data. The agents discuss and agree on the state of your contacts before one is permitted to use `update_contact` to mark an entry as verified. This MCP server provides the tools for that job.

Setup guide

Set up Avochato 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 Avochato 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="Avochato_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Each agent in the conversation can be equipped with the same set of Avochato tools. They take turns speaking, and when it's an agent's turn, it can choose to execute a tool like `send_message` or `list_tickets`.

Yes. You can create a 'SupportAgent' that uses `list_tickets` to find work, and an 'EngineerAgent' that it can talk to. They can collaborate on a solution before the support agent uses `update_ticket`.

Absolutely. One agent can draft a message as text, and another agent can review it, approve it, and then execute the `send_message` tool with the text. This enables review and approval workflows.

A 'Sales' agent uses `create_contact` for a new lead. A 'Data' agent then uses `list_contacts` and flags it as a potential duplicate. They debate until the Sales agent uses `update_contact` to merge the info.

Data like ticket details or message content is passed as text within the agent conversation. It exists in the transient memory of the chat. The Vinkius server is stateless, and you control the logging and persistence of the agent conversation itself.

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