How to Use the Tower MCP in AutoGen

Q: How does AutoGen use Tower MCP Server for project planning?

Agents can debate the scope of work by cross-referencing listprojects and getproject. They negotiate what information is necessary, leading to a refined understanding of the goal.

Q: Can AutoGen handle complex updates with Tower?

Yes. If you need to update a task using updatetask, multiple agents can argue over the best timing or required approvals before allowing the final tool call, making the process accountable.

Achieve consensus decisions with AutoGen and Tower MCP Server. Multi-agent debate system.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Tower MCP to AutoGen

Create your Vinkius account to connect Tower 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 Tower with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate Task Requirements

You can initiate a task creation process by calling `create_task` and having multiple agents argue over the best parameters. One agent might flag that more details are needed, while another suggests a default priority. The result is a consensus-driven decision on how to set up the task, ensuring no critical piece of information is overlooked.

Verify Project Status

Set up agents to check project status using `list_projects` and then follow up with `list_tasks`. A 'Risk Agent' can challenge a high-priority task, while a 'Performance Agent' verifies the completion metrics. The system debates the true readiness of the project before reporting back a final, negotiated status.

Coordinate Team Assignments

Use `list_members` to gather all available personnel. Then, have agents cross-reference that list with `list_teams` to ensure appropriate coverage. The multi-agent setup doesn't just list names; it simulates a resource allocation meeting, identifying overlaps or gaps in team assignments.

Setup guide

Set up Tower 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 Tower 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="Tower_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Agents can debate the scope of work by cross-referencing `list_projects` and `get_project`. They negotiate what information is necessary, leading to a refined understanding of the goal.

Yes. If you need to update a task using `update_task`, multiple agents can argue over the best timing or required approvals before allowing the final tool call, making the process accountable.

The system uses member roles and group affiliations. By combining `list_members` and `list_teams`, agents can identify who has the necessary skills or access level for a given task.

It’s designed exactly for that. If an answer requires deliberation—say, determining if two teams conflict—the agents will debate the issue until a consensus is reached.

The server touches Team Names, Member User IDs, Project Titles, Task Priorities, and Discussion Summaries. These structured strings are the core inputs for agent debate.

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