How to Use the Sunsama MCP in AutoGen

Drive consensus decisions on Sunsama tasks with AutoGen and the MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sunsama MCP to AutoGen

Create your Vinkius account to connect Sunsama 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 Sunsama with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Resolve task conflicts through agent debate.

You can't just ask one agent to fix a schedule conflict. Instead, let multiple agents—a Planner Agent and an Executor Agent—debate the best approach by calling `get_task_details()` repeatedly. They challenge each other’s assumptions until they reach consensus. The MCP Server provides the ground truth data for this debate. Agents use tools like `create_task` or `update_task` only after achieving a negotiated conclusion.

Simulate full lifecycle task management.

Want to test how a new project rollout goes? Set up an agent system where one agent calls `list_channels()` and another uses that data point to call `create_task()`. They negotiate the best naming convention or initial scope. This multi-agent conversation approach handles complexity far better than simple sequential execution.

Verify user status across multiple roles.

Multiple agents can query the same source of truth. One agent calls `get_user_profile()` for payroll data, while another uses it to validate access rights via `list_contexts()`. They discuss if the profile details are sufficient for the required action. The system forces a consensus check on user identity before any write operation happens.

Setup guide

Set up Sunsama 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 Sunsama 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="Sunsama_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Instead of simple execution, AutoGen makes agents debate the best action. If two tasks conflict, one agent can flag it using `get_task_details`, and another can propose a fix via `update_task`, forcing a mediated resolution.

Yes. You build scenarios where the answer isn't obvious. For example, having one agent check available time slots (`list_tasks`) and another agent challenge that availability against user priorities.

The server touches task text and planned dates. In a multi-agent setup, you must assign specific agents to read sensitive tools like `get_user_profile()` and ensure their output is restricted.

It's useful when the workflow requires deliberation. If you just need a single step (like 'create task'), LangChain works fine. But if you need Agent A to challenge Agent B’s idea, AutoGen is your tool.

Start by creating a debate between two agents: one that calls `list_tasks` and another that tries to use that data to call `delete_task`. Watch them negotiate whether deletion is safe or necessary.

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