How to Use the Sobot MCP in AutoGen

Q: What happens when multiple tools are needed with Sobot and AutoGen?

Agents are assigned specific tool sets (e.g., Agent A gets listtickets, Agent B gets getagentstatus). They exchange the results of these calls to build their case for a final decision.

Q: What data types are involved when running multi-agent processes with Sobot and AutoGen?

The process touches user profiles (listusers), ticket content (getticketdetails), and detailed chat logs (listchathistory). All this data is used for debate.

Run Consensus Decisions on Sobot with AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sobot MCP to AutoGen

Create your Vinkius account to connect Sobot to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Sobot with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Debating Ticket Escalation Paths

Instead of one agent deciding the next step, you can set up a debate. One agent reviews `get_ticket_details` for complexity, another checks `list_agents` for expertise, and a third assesses urgency using `list_tickets`. The system must reach consensus on who gets the ticket. This multi-agent structure simulates deliberation, ensuring that no single perspective dictates the outcome.

Achieving Consensus on User Information

You can assign agents roles: one reviews `list_users` for basic identification, another checks `get_org_summary` for corporate status. The agents then debate which data point is the most critical to create a ticket, forcing a comprehensive decision. This consensus model prevents single points of failure in complex routing logic.

Simulated Chat History Analysis

Need a definitive summary? You can assign agents to analyze `list_chat_history`. One agent summarizes the emotional tone, while another focuses strictly on technical keywords. They then debate and generate a single, agreed-upon root cause analysis. It's about forcing different viewpoints onto a single problem until a unified conclusion emerges.

Setup guide

Set up Sobot 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 Sobot 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="Sobot_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

The system doesn't execute linearly. Multiple agents discuss the task, challenging each other's assumptions and negotiating until a consensus decision is reached for action.

Agents are assigned specific tool sets (e.g., Agent A gets `list_tickets`, Agent B gets `get_agent_status`). They exchange the results of these calls to build their case for a final decision.

Yes. You can run an internal debate where one agent verifies `get_org_summary` against another agent's assumptions about the organization's current state, ensuring accuracy.

The process touches user profiles (`list_users`), ticket content (`get_ticket_details`), and detailed chat logs (`list_chat_history`). All this data is used for debate.

The framework manages context across multiple conversational turns. Each agent's output informs the next round of deliberation, allowing the system to maintain a working memory of the problem.

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