How to Use the Middesk MCP in AutoGen

Build debating agents in AutoGen that use Middesk to negotiate business verification outcomes and compliance decisions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Middesk MCP to AutoGen

Create your Vinkius account to connect Middesk 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 Middesk with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enable agent debate on KYB

Assign one agent to check `get_business` records while another critiques the risk profile. AutoGen manages the negotiation, ensuring both agents agree before finalizing a verification. This prevents the common issue of single-agent bias. You get a second opinion on every business entity automatically.

Automate compliance with multiple agents

Use `list_tax_registrations` to feed data into your debate loop. If the tax status is unclear, the agents challenge each other to find more documentation. It forces a consensus based on evidence. You end up with a clear, audited decision path for every merchant you onboard.

Negotiate document requirements

Your agents use `list_documents` to determine if a file is sufficient. If the document is outdated, the agents discuss whether to request a new one or flag the account. This removes the need for you to oversee every step. The agents handle the back-and-forth until the criteria are met.

Setup guide

Set up Middesk 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 Middesk 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="Middesk_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You pass the Middesk tools directly to the AssistantAgent constructor via the MCP adapter. This allows your agents to call the API as part of their conversation.

That is the point. You can set up a system where a performance agent pushes for speed while a security agent demands more documents from the Middesk server.

The adapter handles both stdio and HTTP transports. You just need to provide the correct configuration to the server tools function.

The server provides the data, and the agents deliberate based on the content. Vinkius keeps the connection ephemeral to protect your business records.

Every tool execution is authenticated via your endpoint token. Agents only see the data returned by the tools they are authorized to call.

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