Condeco (Eptura Engage) MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Condeco (Eptura Engage) through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="Condeco (Eptura Engage) Assistant",
instructions=(
"You help users interact with Condeco (Eptura Engage). "
"You have access to 10 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Condeco (Eptura Engage)"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Condeco (Eptura Engage) MCP Server
Connect your Condeco (now Eptura Engage) account to any AI agent and take full control of your enterprise workspace and desk booking workflows through natural conversation.
The OpenAI Agents SDK auto-discovers all 10 tools from Condeco (Eptura Engage) through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Condeco (Eptura Engage), another analyzes results, and a third generates reports, all orchestrated through Vinkius.
What you can do
- Office Location Navigation — Identify bounded office capacities and geographic groupings mapping explicitly tracked buildings and campuses
- Room Management — Enumerate available meeting spaces, filtering by capacity and AV features, and check real-time usage states
- Desk & Hot Desking — Claim exclusive usage of hot desks within specific neighborhoods and zones, including equipment filters
- Live Reservations — Mutate active scheduling endpoints to book or cancel rooms and desks with instant sync to O365/Exchange
- Check-in Automation — Trigger physical presence capabilities to confirm your arrival at a location and satisfy local access controls
- Booking History — Extract chronological logs of user reservations to audit space utilization across your organization
The Condeco (Eptura Engage) MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Condeco (Eptura Engage) to OpenAI Agents SDK via MCP
Follow these steps to integrate the Condeco (Eptura Engage) MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 10 tools from Condeco (Eptura Engage)
Why Use OpenAI Agents SDK with the Condeco (Eptura Engage) MCP Server
OpenAI Agents SDK provides unique advantages when paired with Condeco (Eptura Engage) through the Model Context Protocol.
Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Condeco (Eptura Engage) + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Condeco (Eptura Engage) MCP Server delivers measurable value.
Automated workflows: build agents that query Condeco (Eptura Engage), process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents. one queries Condeco (Eptura Engage), another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Condeco (Eptura Engage) tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Condeco (Eptura Engage) to resolve tickets, look up records, and update statuses without human intervention
Condeco (Eptura Engage) MCP Tools for OpenAI Agents SDK (10)
These 10 tools become available when you connect Condeco (Eptura Engage) to OpenAI Agents SDK via MCP:
book_desk
Claim exclusive usage targeting specific hot desking bounds
book_room
Claim exclusive scheduling capabilities tracing synchronization triggers upon physical spaces
cancel_desk_booking
Revoke claimed exclusive desk reservations natively
cancel_room_booking
Revoke exact chronological reservations matching O365 sync boundaries
check_in_to_location
Trigger physical presence capabilities executing explicit local access controls
get_room_availability
Determine real-time usage states extracting explicit chronological meeting blocks
list_bookings
Extract chronological logs resolving explicit user booking reservations
list_desks
Identify specific bounding capacities covering mapped hot desks
list_locations
Identify bounded office capacities discovering standard enterprise real estate limits
list_rooms
Enumerate explicitly mapped meeting spaces filtering capacity and feature sets
Example Prompts for Condeco (Eptura Engage) in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Condeco (Eptura Engage) immediately.
"List all meeting rooms in the 'New York HQ' location"
"Book room 101 for tomorrow from 2:00 PM to 3:00 PM with title 'Weekly Sync'"
"I've arrived at the office. Check me in to location 50"
Troubleshooting Condeco (Eptura Engage) MCP Server with OpenAI Agents SDK
Common issues when connecting Condeco (Eptura Engage) to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Condeco (Eptura Engage) + OpenAI Agents SDK FAQ
Common questions about integrating Condeco (Eptura Engage) MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect Condeco (Eptura Engage) with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Condeco (Eptura Engage) to OpenAI Agents SDK
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.
