How to Use the Workast MCP in AutoGen

Q: What specific Workast data types are touched by AutoGen?

This MCP Server handles Spaces (listspaces), Users (getuser), and Tasks. The debate process requires access to these three core resource types.

Q: If I delete a task, how does AutoGen handle it? Workast and AutoGen?

An agent can propose the deletion using deletetask. Another agent can challenge that proposal by checking dependencies or required permissions before allowing the action to proceed.

Force Workast decisions through debate using AutoGen's multi-agent framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Workast MCP to AutoGen

Create your Vinkius account to connect Workast 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 Workast with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus on MCP Server Actions

Agents don't just run tools; they argue about which ones to run. If you need a new space, one agent might call `create_space`, while another challenges it by checking existing spaces via `list_spaces` first. They deliberate until consensus is reached. This makes the MCP Server an active participant in complex decision-making processes between multiple specialized agents.

Structured Workast Planning

Use different agents to model different perspectives on your project. One agent can handle resource allocation by listing team users (`list_users`). A second agent might then call `get_task` to check if those users actually have access to the required space. The debate process forces a thorough vetting of the necessary steps, leading to highly validated action plans.

Handling Workast Updates via Debate

If you're updating a critical task (`update_task`), one agent might flag potential conflicts (a risk assessment), while another insists on speed. They negotiate the best payload and timing, using `get_task` data as their starting point. The MCP Server functions here not just as an executor, but as a subject of debate among specialized AI agents.

Setup guide

Set up Workast 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 Workast 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="Workast_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You pass the MCP Server's tool list to the AssistantAgent. The agents then use this tool set—like `get_user` or `list_spaces`—as potential actions during their conversation and debate.

Multiple agents discuss the goals. They might decide that to complete a goal, they first need `get_team_info`, then they'll use that data to formulate a plan for creating resources.

This MCP Server handles Spaces (`list_spaces`), Users (`get_user`), and Tasks. The debate process requires access to these three core resource types.

Yes, the multi-agent setup is perfect for complex planning. Agents can challenge each other on whether `create_task` is appropriate or if a more detailed `get_space` check is needed first.

An agent can propose the deletion using `delete_task`. Another agent can challenge that proposal by checking dependencies or required permissions before allowing the action to proceed.

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