How to Use the Condeco (Eptura Engage) MCP in AutoGen

Q: How do I register Condeco (Eptura Engage) tools with AutoGen agents?

You use mcpservertools with StreamableHttpServerParams pointing to your Vinkius URL. This automatically converts tools like bookdesk into schemas that your AutoGen AssistantAgent can understand.

Q: Can AutoGen agents debate which Condeco (Eptura Engage) room to book?

Yes, you can set up one agent to find rooms using listrooms and another to verify constraints. They debate the best option in the group chat before the executor agent calls bookroom.

Q: How do AutoGen agents handle conflicting bookings in Condeco?

When bookdesk returns a conflict error, your AutoGen agents discuss alternative solutions. They immediately query listdesks to find a nearby workspace and complete the booking without failing the workflow.

Run multi-agent debates in AutoGen to coordinate Condeco (Eptura Engage) room bookings and resolve scheduling conflicts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Condeco (Eptura Engage) MCP to AutoGen

Create your Vinkius account to connect Condeco (Eptura Engage) 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 Condeco (Eptura Engage) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent room booking negotiation in AutoGen

Your AutoGen agents coordinate physical space allocations by calling `book_room` through the Condeco (Eptura Engage) MCP Server. A scheduling agent proposes a room, while a policy agent checks if the reservation complies with company rules before executing. This collaborative setup ensures that meeting spaces are booked efficiently. The agents use `get_room_availability` to resolve conflicts autonomously before writing any reservations to Condeco.

Automated desk cancellation and reallocation

The `cancel_desk_booking` tool lets your AutoGen agents manage hot desk allocations when team schedules shift. A coordination agent monitors user calendars and tells the booking agent to release a desk when an employee calls in sick. You register these capabilities using `mcp_server_tools` and pass them to your `AssistantAgent`. The agents talk to each other to ensure that `list_desks` is run and empty workspaces are reassigned to waiting employees.

Location verification and check-in tracking

The `check_in_to_location` tool allows your AutoGen security agent to verify physical attendance against office boundaries. When a user arrives, the agent runs `list_locations` to confirm the office capacity limits are respected. If a user fails to check in, the coordination agent can automatically run `cancel_room_booking` to free up the meeting room. This multi-agent loop keeps your physical office running smoothly without human oversight.

Setup guide

Set up Condeco (Eptura Engage) 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 Condeco (Eptura Engage) 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="Condeco (Eptura Engage)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Condeco (Eptura Engage) 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="Condeco (Eptura Engage)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Condeco (Eptura Engage) 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 Condeco. 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 Condeco (Eptura Engage) 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 Condeco (Eptura Engage) MCP in AutoGen

You use mcp_server_tools with StreamableHttpServerParams pointing to your Vinkius URL. This automatically converts tools like book_desk into schemas that your AutoGen AssistantAgent can understand.

Yes, you can set up one agent to find rooms using list_rooms and another to verify constraints. They debate the best option in the group chat before the executor agent calls book_room.

Yes, the Condeco (Eptura Engage) server connects natively via Streamable HTTP. This allows your AutoGen framework to run MCP tool calls like list_bookings across distributed agent networks.

When book_desk returns a conflict error, your AutoGen agents discuss alternative solutions. They immediately query list_desks to find a nearby workspace and complete the booking without failing the workflow.

This MCP Server secures your office booking schedules using ephemeral V8 sandboxing. Vinkius processes your physical desk coordinates and user IDs in isolation, ensuring no sensitive data is leaked during multi-agent debates.

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