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

Q: Can I trace Condeco (Eptura Engage) tool calls in LangChain using LangSmith?

Yes, every call to listbookings or bookroom shows up in your LangSmith dashboard with full inputs, outputs, and latency metrics. You can see exactly why your LangChain agent decided to book a specific desk or cancel a room.

Q: What happens if a desk booking fails during a Condeco (Eptura Engage) run in LangChain?

The bookdesk tool returns a clear error message that your LangChain ReAct agent reads. The agent then automatically tries an alternative desk from the listdesks output or alerts the user.

Get your LangChain agents booking physical desks and managing office meeting rooms in Condeco (Eptura Engage) without manual steps.

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 LangChain

Create your Vinkius account to connect Condeco (Eptura Engage) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Dynamic room booking chains in LangChain

Your LangChain chains use the Condeco (Eptura Engage) MCP Server to pull real-time room data via `list_rooms`. The agent instantly checks current schedules using `get_room_availability` and locks down the booking with `book_room`. You don't have to bounce between browser tabs to find a quiet space. Every step of this chain gets tracked in LangSmith, so you can see exactly when and why your agent booked a specific room.

Automated desk cancellation and hot desking

The `list_desks` tool lets your ReAct agent map out hot desking setups across your entire floor plan. When plans change and a user cancels, the agent calls `cancel_desk_booking` to free up that spot instantly. You feed these tools straight into your agent configurations. The agent handles the back-and-forth decisions, keeping your physical office space optimized without you writing custom cron jobs.

Local access control and check-ins

The `check_in_to_location` tool lets your pipeline verify physical presence and trigger local access controls. Your agent checks the office boundaries with `list_locations` before confirming the user has arrived. You can easily pair these security tools with other LangChain integrations. This lets you build workflows that sync physical check-ins with your team's internal status boards.

Setup guide

Set up Condeco (Eptura Engage) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Condeco (Eptura Engage) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "condeco-eptura-engage-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Condeco (Eptura Engage) transactions"
    })
    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 LangChain

You configure the connection using the Vinkius single endpoint token inside your MultiServerMCPClient setup. This single token handles all authentication behind the scenes, so your LangChain agents can execute tools like book_desk without managing separate Condeco credentials.

Yes, every call to list_bookings or book_room shows up in your LangSmith dashboard with full inputs, outputs, and latency metrics. You can see exactly why your LangChain agent decided to book a specific desk or cancel a room.

Install langchain-mcp-adapters, initialize the MCP client with your Vinkius HTTP URL, and call client.get_tools(). You then pass this tool list directly to your agent constructor to enable real-time office booking.

The book_desk tool returns a clear error message that your LangChain ReAct agent reads. The agent then automatically tries an alternative desk from the list_desks output or alerts the user.

This MCP Server processes your physical desk coordinates and room schedule data inside a secure, ephemeral V8 isolate sandbox. Vinkius ensures your Condeco corporate directory details never persist on external servers.

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