How to Use the Duda MCP in AutoGen

Q: How do AutoGen agents collaborate on a Duda site audit?

One agent runs quicksitehealthaudit to get metrics, while another reviews the results. They debate the health score in a conversational loop to decide if manual intervention is required.

Q: Can AutoGen manage Duda client permissions automatically?

Yes. An agent calls getclientaccountprofile to retrieve current permissions. A supervisor agent then reviews the data to ensure it aligns with your security policies before approving access.

Q: How do I register the Duda MCP Server in AutoGen?

Use mcpservertools with your server HTTP endpoint to fetch the tool definitions. AutoGen automatically registers the tools so your agents can call them during their conversations.

Q: How do agents find a specific site in a large account?

Your agents use searchsitesbydomain to find the exact site ID. This prevents them from wasting tokens scanning through long lists of inactive websites.

Let your AutoGen agents debate site health audits and client configurations before publishing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Duda MCP to AutoGen

Create your Vinkius account to connect Duda 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 Duda with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent verification of site health

Set up a debate between a performance agent and a QA agent. The first agent calls `quick_site_health_audit` to pull activity metrics, while the second uses `list_published_websites` to check publication status. Together, they negotiate whether a site is ready for public release. This MCP Server setup ensures no site goes live without consensus, reducing deployment errors.

Collaborative client onboarding checks

Simplify team alignment during onboarding. An agent calls `list_client_accounts` to check current users, then queries `get_client_account_profile` to verify permissions. Another agent reviews the profiles against company policy. They discuss the settings in a conversational loop, only finalizing the account once all policy checks pass.

Collaborative template selection

Let your agents select templates via MCP based on client constraints. One agent pulls options via `list_site_templates` while another analyzes the client's business profile using `get_template_details`. The agents debate which layout fits the client's industry best. Once they agree, they output the selected template ID, ready for automated site provisioning.

Setup guide

Set up Duda 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 Duda 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="Duda_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

One agent runs `quick_site_health_audit` to get metrics, while another reviews the results. They debate the health score in a conversational loop to decide if manual intervention is required.

Yes. An agent calls `get_client_account_profile` to retrieve current permissions. A supervisor agent then reviews the data to ensure it aligns with your security policies before approving access.

Use `mcp_server_tools` with your server HTTP endpoint to fetch the tool definitions. AutoGen automatically registers the tools so your agents can call them during their conversations.

Your agents use `search_sites_by_domain` to find the exact site ID. This prevents them from wasting tokens scanning through long lists of inactive websites.

Your API tokens are managed via secure environment variables in an ephemeral runtime environment. Client account profiles and database collection schemas are never exposed to public LLM endpoints.

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