How to Use the Adversus MCP in AutoGen

Q: How do I initialize Adversus MCP tools in AutoGen?

Install autogen-extmcp via pip. Use mcpservertools with StreamableHttpServerParams pointing to your Vinkius URL, then pass the tools to your AssistantAgent.

Let agents debate your sales strategy. AutoGen negotiates Adversus campaign assignments before moving a single contact.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Adversus MCP to AutoGen

Create your Vinkius account to connect Adversus 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 Adversus with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Negotiate Lead Placements

Dropping every new prospect into the same queue destroys call center efficiency. You set up a performance agent that wants aggressive dialing, while a compliance agent watches the bounce rates. They pull the global queue using `list_active_leads` and start arguing about where to put them. Once the two bots reach a consensus, the system executes the decision via this MCP integration. It fires `add_contact_to_campaign` only after both perspectives agree on the target. You get a balanced outbound strategy without manually reviewing every record.

Audit AutoGen MCP Server Campaigns

Managers rarely have time to check every active dialing list. An auditor agent runs `list_campaigns` and flags anything with low engagement. A separate manager agent reviews those flags and proposes adjustments based on historical trends. The agents dig deeper by executing `get_campaign_details` on the flagged items. They discuss the configuration settings and identify bottlenecks in the routing logic. The final output is a negotiated summary of what needs fixing.

Balance Team Workloads

Sales reps complain when the lead distribution feels unfair. Your AutoGen system pulls the current roster by calling `list_account_users` to see who is online. A resource agent maps out the available manpower across the floor. A secondary agent checks the actual volume by running `list_campaign_contacts` across active projects. They debate the current assignments and suggest reallocating prospects to idle reps. The human operator just approves the final, logical plan.

Setup guide

Set up Adversus 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 Adversus 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="Adversus_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]` via pip. Use `mcp_server_tools` with `StreamableHttpServerParams` pointing to your Vinkius URL, then pass the tools to your AssistantAgent.

Yes. You can provide the same tool list to every agent in the conversation. The framework handles schema conversion automatically via `McpToolAdapter`.

They continue debating until they reach the maximum turn limit or find a compromise. You define the termination conditions in the conversation configuration.

The Vinkius endpoint supports Streamable HTTP. Your multi-agent setup will maintain the connection while the bots deliberate.

Phone numbers and prospect names live briefly inside isolated memory spaces. The V8 sandbox ensures no external processes can scrape the conversation history. Everything evaporates when the script terminates.

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