How to Use the Whereby MCP in AutoGen

Q: How does AutoGen determine the best time to schedule meetings using Whereby?

Agents debate the optimal parameters, calling tools like getmeetingdetails multiple times. They compare expiration dates and room modes to reach a consensus on the ideal setup before creating it.

Q: Whereby: If I need to list all existing rooms, what tools should AutoGen use?

The agent uses listactivemeetings. This output gives a complete picture of the current status. It can also use listcloudrecordings if it needs context on recorded materials.

Drive consensus on meeting strategy with AutoGen’s multi-agent debate framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Whereby MCP to AutoGen

Create your Vinkius account to connect Whereby 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 Whereby with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debating Meeting Setup

When multiple agents need to decide on a new meeting, they can debate the parameters. One agent might suggest `create_meeting_room` with a 'normal' mode and early end date, while another argues for a 'group' setting and later expiration. The outcome is consensus-driven. The result of this negotiation—the final room setup—is then passed to the user for execution.

Negotiating Branding Standards

A security agent might flag an inconsistent brand, triggering a debate. Another agent can then check existing styles using `get_room_theme`. After arguing over the best color, they converge on a single hex code needed for `update_room_theme`, ensuring system compliance. This means complex style decisions are settled through internal deliberation before any tool is called.

Auditing and Cleaning Up Sessions

Agents can run an audit by calling `list_active_meetings` to see all current rooms. If a meeting is deemed unnecessary, the agents debate whether it should be deleted using `delete_meeting_room`. This decision process adds a crucial layer of risk assessment. The system also allows for permanent cleanup when dealing with recordings via `delete_cloud_recording`.

Setup guide

Set up Whereby 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 Whereby 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="Whereby_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Agents debate the optimal parameters, calling tools like `get_meeting_details` multiple times. They compare expiration dates and room modes to reach a consensus on the ideal setup before creating it.

The process requires deliberation. The agents debate which color is best using `get_room_theme` and eventually agree upon a single hex code to execute the `update_room_theme` tool call.

The agent uses `list_active_meetings`. This output gives a complete picture of the current status. It can also use `list_cloud_recordings` if it needs context on recorded materials.

The agents debate the need for deletion. Once consensus is reached, they execute `delete_meeting_room`, which immediately terminates the video meeting and cleans up resources.

The MCP Server handles room names, ISO 8601 dates, visual theme settings (hex colors/logos), and meeting metadata. These structured inputs are what the agents debate over.

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