How to Use the VivifyScrum MCP in AutoGen

Q: How does VivifyScrum help with multi-agent debates using AutoGen?

You define roles. One agent might use getitem to get the details of a task, and another might challenge those details by calling listwebhooks. They debate the completeness of the data.

Q: If I want to plan sprints using VivifyScrum and AutoGen, how does it work?

You let two agents argue. One agent calls listsprints to get available timelines. The other might call getaccountinfo to confirm resource availability before agreeing on a date.

Q: Can VivifyScrum help AutoGen compare different project contexts?

Yes. Agents can use listboards and then argue over which specific board's data (getboard) is most relevant to the current decision, leading to a converged conclusion.

Build consensus-driven project systems with VivifyScrum and AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect VivifyScrum MCP to AutoGen

Create your Vinkius account to connect VivifyScrum 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 VivifyScrum with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debating task requirements

You can set up agents to debate a new feature. One agent calls `create_item` to draft the story, while another checks dependencies using `get_board`. The agents then negotiate if the story is complete enough. The goal is consensus: getting agreement on whether an item needs further definition or if it's ready for sprint planning.

Validating project status

A 'Validation Agent' can pull current board details via `get_board`. A second agent might then use `list_sprints` to check timeline conflicts. They debate the best path forward for that specific project. This system ensures complex decisions aren't made on incomplete data.

Comparing organizational scopes

Agents can compare different levels of scope. One might list all organizations (`list_organizations`), while another checks teams using `list_teams`. They argue over which group is the most relevant scope for a given task. This deliberation process helps solve ambiguity in large, complex environments.

Setup guide

Set up VivifyScrum 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 VivifyScrum 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="VivifyScrum_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You define roles. One agent might use `get_item` to get the details of a task, and another might challenge those details by calling `list_webhooks`. They debate the completeness of the data.

You let two agents argue. One agent calls `list_sprints` to get available timelines. The other might call `get_account_info` to confirm resource availability before agreeing on a date.

Yes. Agents can use `list_boards` and then argue over which specific board's data (`get_board`) is most relevant to the current decision, leading to a converged conclusion.

The server handles project metadata, including account details, team lists, board information, and item descriptions. This is the core operational data set.

You simply give two agents the goal: 'Identify all active teams.' One agent calls `list_teams` and another validates that list against available organizations using `list_organizations`.

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