How to Use the Simplicate MCP in AutoGen

Achieve consensus decisions with AutoGen: Multi-agent Benelux professional services architecture.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Simplicate MCP to AutoGen

Create your Vinkius account to connect Simplicate 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 Simplicate with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Debating Project Status and Risks

You build systems where multiple agents debate a conclusion. For instance, one agent checks the current project status using `get_project_details`, while another agent (the 'Risk Agent') flags potential issues by checking sales opportunities via `list_sales_opportunities`. They negotiate to give you a final, consensus-driven recommendation. This is perfect for complex client reviews. Instead of one answer, you get a discussion that weighs immediate profitability against long-term client relationships. It's built around deliberation.

Validating Financial Data Consensus

Multiple agents can challenge financial data inputs. One agent might pull all invoices using `list_invoices`, while a second agent verifies the underlying service scope by calling `list_project_services`. They debate whether the listed services match the invoiced items, flagging discrepancies for you. This consensus mechanism is key. It forces cross-validation across tools like `get_my_organization_profile` and `list_invoices`, ensuring that every piece of financial data has been vetted by different perspectives.

Coordinating Personnel Actions

Need to hire or reassign staff? You can set up agents that debate the best course of action. One agent checks available personnel via `list_employees`, while another verifies if the individual is assigned to a relevant project using `get_project_details`. The negotiation results in an actionable staffing plan. This structured deliberation process handles ambiguity better than simple linear scripts. It simulates real-world management discussions, improving decision quality across your firm's operations.

Setup guide

Set up Simplicate 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 Simplicate 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="Simplicate_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

AutoGen uses multiple specialized agents that discuss and challenge each other. The final answer isn't the result of a single tool call; it’s the consensus reached after internal debate, making the outcome highly reliable.

Yes. You can assign agents with opposing goals—like one focused on speed and another on compliance. They will negotiate and converge on a solution that satisfies both competing perspectives, which is invaluable in professional services.

This server touches organization profiles, project details, sales opportunities, employee lists, invoices, time registrations, and contact information. The multi-agent system ensures that access controls are applied during the deliberation process.

It excels at this because complex regulations often require input from several departments (sales, finance, HR). The multi-agent debate ensures that all relevant angles—and thus potential compliance risks—are considered.

You can set up agents to plan workflows by making them negotiate the best sequence of actions. For example, they might decide that checking project details must happen before confirming billing eligibility.

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