How to Use the SEON MCP in AutoGen

Q: Can I use AutoGen for complex transaction monitoring with SEON?

Yes. You can create an 'Audit Agent' that pulls gettransaction details and feeds them into the debate, while another agent runs listamlmonitors to check compliance requirements.

Get consensus on risk decisions with AutoGen's multi-agent debate.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect SEON MCP to AutoGen

Create your Vinkius account to connect SEON 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 SEON with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

AutoGen: Debate Fraud Risk

Multiple agents challenge each other’s conclusions. You can set up a 'Security Agent' that runs `aml_screening`, while a 'Performance Agent' pushes back on false positives, forcing the system to negotiate a final risk score. This consensus-driven model is perfect when no single tool call provides enough information; it requires deliberation.

MCP Server: Multi-Perspective Data Review

A debate structure can process disparate data points. One agent pulls `get_account_info`, another runs `check_ip` risk checks, and a third reviews `list_rules`. The final decision is only reached after all three perspectives have been considered. This ensures that critical decisions aren't based on just one single indicator or tool output.

AutoGen: Dispute Resolution for Transactions

Use the multi-agent setup to resolve disputes. One agent flags a transaction using `check_fraud`, and another agent runs `add_to_list` checks against blacklists/whitelists (`list_lists`). They debate whether the risk warrants immediate action or manual review. This is ideal for complex edge cases where multiple rules might apply simultaneously.

Setup guide

Set up SEON 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 SEON 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="SEON_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You assign specific tools to agents. For instance, one agent's job is solely to run `check_phone` and report the findings, while another agent uses that input to decide on a final action.

Yes. You can create an 'Audit Agent' that pulls `get_transaction` details and feeds them into the debate, while another agent runs `list_aml_monitors` to check compliance requirements.

This SEON server deals with PII like email and phone numbers. In an AutoGen flow, you must structure the agents so that only authorized agents can access and debate sensitive identity data.

It's built for it. You give conflicting requirements to different agents—one agent reads `list_rules`, another reviews the transaction context—and they debate which rule takes precedence.

Absolutely. You can run a persistent conversation loop where agents continuously challenge each other on new incoming data, keeping your risk scoring model constantly vigilant.

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