How to Use the KanbanTool MCP in AutoGen

Q: How do AutoGen agents access KanbanTool functions?

Use the mcpservertools function from the AutoGen MCP extension. Point it to your server endpoint, and it returns a list of tools you pass directly to your AssistantAgent constructor. The adapter handles the rest.

Q: Can two AutoGen agents argue about a KanbanTool task's priority?

Yes, that's a core AutoGen pattern. One agent can use gettaskdetails to argue based on the task description, while another uses listtaskactivities to argue based on recent comments. They converge on a decision through conversation.

Deploy AutoGen agent teams to debate, plan, and execute complex KanbanTool workflows, ensuring every action is verified.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect KanbanTool MCP to AutoGen

Create your Vinkius account to connect KanbanTool 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 KanbanTool with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Agents Debate a Release Plan

Use a multi-agent system to build bulletproof release plans. A 'Planner' agent can propose a task sequence by calling `list_board_tasks`. A 'QA' agent then challenges that plan, using `get_task_details` to check if each task is actually ready for deployment. They discuss and debate until they reach a consensus. Only then does an 'Executor' agent take the approved list and update each card's status with `update_task_details`. It's a workflow built on deliberation.

Create a Multi-Agent Cleanup Crew

Board hygiene is a constant battle. Set up two agents to automate it. A 'Scanner' agent runs `list_board_tasks` and `list_task_activities` to find old, inactive cards, then proposes a list of cards to archive. It passes that list to a 'Reviewer' agent, which can double-check the card owner with `get_user_profile` or look for 'DO NOT ARCHIVE' labels. Only when they agree in the chat does one of them get permission to call `archive_task_card`. No more accidental archiving.

Onboard New Hires with an AutoGen Agent

Build a conversational onboarding process. A 'Mentor' agent can be tasked with setting up a new hire's board. It calls `create_task_card` to add a standard set of onboarding tasks like 'Request database access' and 'Complete compliance training'. Then, the user (or a 'New Hire' proxy agent) can ask the Mentor for help. The Mentor agent uses `get_task_details` to check on progress and `update_task_details` to add helpful comments or links. The whole process is driven by the agent conversation.

Setup guide

Set up KanbanTool 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 KanbanTool 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="KanbanTool_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use the `mcp_server_tools` function from the AutoGen MCP extension. Point it to your server endpoint, and it returns a list of tools you pass directly to your `AssistantAgent` constructor. The adapter handles the rest.

Yes, that's a core AutoGen pattern. One agent can use `get_task_details` to argue based on the task description, while another uses `list_task_activities` to argue based on recent comments. They converge on a decision through conversation.

You design the agent interaction to require consensus. For example, an `ExecutorAgent` can call `archive_task_card`, but you configure it to only act after a `ReviewerAgent` gives an explicit 'LGTM' in the chat.

Of course. You can tell your agent group, "We need a ticket for the login page bug." One of the agents will take that instruction and call `create_task_card` with the right board name and title.

Your project data, such as task content and user info, is passed through Vinkius's stateless MCP server directly to the KanbanTool API. The conversation history between your AutoGen agents, which may reference this data, is managed by your local AutoGen environment.

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