How to Use the Kisi MCP in OpenAI Agents SDK

Control physical doors and manage building access directly from your production-grade OpenAI Agents SDK workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kisi MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Secure Door Control with OpenAI Agents SDK Guardrails

The `unlock_door` tool acts as the primary mechanism for physical entry, firing a direct POST request to the specified hardware lock. When you run this within your python agent, the OpenAI Agents SDK intercepts the call, running your custom validation logic to verify the user's location before the lock physically clicks open. This setup prevents unauthorized entry by forcing every execution through your defined safety layers. By checking `get_lock_details` before triggering the command, the MCP Server confirms the current hardware status and logs the exact event to your OpenAI dashboard.

Automated Organization Mapping and Access Audits

Running `list_places` returns every physical location bound to your organization, providing the base geography for your security logic. Your OpenAI Agents SDK workflow uses this spatial data to cross-reference active lock configurations, querying `list_locks` to map out the physical footprint of your offices. Matching these roles against the active groups returned by `list_access_groups` allows the agent to build a live, in-memory map of your facility's security posture inside the OpenAI agent context.

Real-Time User Verification and Profile Matching

Pulling directory records with `list_users` provides the complete list of registered personnel directly inside your agent's execution context. This allows the MCP integration to match incoming chat requests against actual employee records, ensuring that only verified staff can request door state changes via the OpenAI Agents SDK. To confirm identity, the agent calls `get_my_profile` to check the caller's active session details. Verification finishes when the agent queries `get_place_details` to verify if the user's assigned building matches their current physical work location before the OpenAI agent executes any command.

Setup guide

Set up Kisi 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 Kisi tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Kisi 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="Kisi Agent",
            instructions="You have access to Kisi 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 Kisi. 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 Kisi 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 Kisi MCP in OpenAI Agents SDK

You install the library via pip, instantiate the HTTP server class with your Vinkius endpoint, and register it directly in your agent's server list. The framework automatically discovers the 9 tools, making physical entry management immediately available to your model.

Yes, you handle this by setting up custom guardrails in your agent's constructor. You can block the `unlock_door` tool entirely for certain agent roles, allowing them only to read configurations using `list_locks`.

The Python SDK handles the connection stream, but the underlying Vinkius infrastructure absorbs the initial connection overhead. If the Kisi API throws a rate limit during a heavy run of `list_users`, the agent catches the error and can retry based on your backoff policy.

The agent receives a standard API failure response from the `unlock_door` call. It parses the error payload, checks the lock state using `get_lock_details`, and can hand off the task to a human admin if the hardware is unresponsive.

The integration runs inside a zero-trust V8 sandbox, meaning your raw user IDs, lock states, and role assignments are never stored on Vinkius. Your agent communicates directly with the Kisi API via encrypted HTTPS channels, keeping your physical entry logs isolated from external exposure.

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