How to Use the Envoy MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK check visitor logs using this Envoy integration?

Yes. Your agent invokes listvisitors to see who is checked in or expected at any office. You can trace these tool calls directly inside your OpenAI developer dashboard.

Get your OpenAI Agents SDK system handling desk bookings and visitor registrations on autopilot.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Envoy MCP to OpenAI Agents SDK

Create your Vinkius account to connect Envoy to OpenAI Agents SDK 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 Envoy with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Claim desks directly through OpenAI Agents SDK

The `reserve_desk` tool lets your agent book desks in real-time. This integration exposes desk scheduling directly to your agent, turning natural language requests into instant office space assignments without manual overhead. Your agent checks available spots using `list_desks` before making a move. It handles the whole booking cycle, ensuring nobody shows up to a packed office without a workspace.

Secure visitor management with OpenAI Agents SDK

The `pre_register_visitor` tool lets your agent register guests safely before they arrive. By connecting this MCP Server, your agent can draft invite details, run them through your safety checks, and then commit the invite directly to Envoy. Your system can also call `list_visitors` to verify who is scheduled to arrive at any given location. The agent manages the guest lifecycle without risking accidental double-bookings or unauthorized entries.

Track real-time capacity with this Envoy MCP Server

The `get_capacity` tool tracks office density directly from your production Python agent. The server exposes real-time occupancy data to help your agent coordinate team schedules based on actual physical space limits. Instead of manual headcounts, your agent pulls actual sign-in data with `get_employee_signins`. This lets your system warn employees if the office is too crowded before they try to reserve a spot.

Setup guide

Set up Envoy MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Envoy tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Envoy tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Envoy tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Envoy Agent",
            instructions="You have access to Envoy tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Envoy. 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 Envoy 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 Envoy MCP in OpenAI Agents SDK

Look, here's the thing: you register the Envoy MCP Server in your async streamable HTTP context. The agent automatically discovers `reserve_desk` and `cancel_desk_reservation`, letting you run safety guardrails before any booking is committed.

Yes. Your agent invokes `list_visitors` to see who is checked in or expected at any office. You can trace these tool calls directly inside your OpenAI developer dashboard.

You can set up a front-line routing agent that hands off to a specialized workplace agent. The workplace agent receives the `list_locations` and `list_rooms` tools to handle physical office logistics while keeping your main agent lightweight.

Install the SDK and pass the Envoy server URL to the streamable HTTP parameters. Set the cache tools option to true so your agent doesn't waste time fetching the tool schema on every run.

All visitor logs and employee sign-in records stay in your local Vinkius MCP sandbox. Your API keys are encrypted at rest, and your agent only accesses `get_employee_signins` or `list_visitors` during the active execution context.

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