How to Use the Kisi MCP in OpenAI Agents SDK

Q: How do I configure the Kisi MCP Server with the OpenAI Agents SDK?

Install the package via pip install openai-agents. Initialize MCPServerStreamableHttp with your endpoint URL. Pass it to the Agent constructor in the mcpservers array, and tools auto-discover immediately.

Q: Can OpenAI Agents SDK trace when Kisi doors open?

Yes. Every time the agent calls unlockkisilock, the execution trace hits your dashboard. You see the exact payload sent and the latency of the hardware response.

Q: How do I cache Kisi lock data in the OpenAI Agents SDK?

Set cacheToolsList=True when configuring your server parameters. This prevents the agent from fetching the schema repeatedly, cutting down latency when running frequent listkisilocks operations.

Q: What happens if the API goes down during an MCP operation?

The agent catches the failure when calling checkkisistatus or any other endpoint. Your guardrails define the fallback behavior, like alerting a human operator instead of retrying blindly.

Connect the Kisi MCP Server to the OpenAI Agents SDK to build production-grade physical access systems with built-in guardrails.

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

Trigger Emergency Protocols Safely

The `lockdown_kisi_lock` tool instantly drops physical doors into a restricted state during an incident. Your agent executes this command through the framework, but only after passing your predefined safety guardrails. Security requires absolute certainty. You set constraints that force the agent to verify the incident severity before acting. Once cleared, the agent fires the lockdown and logs the exact trace to your dashboard for auditing.

OpenAI Agents SDK MCP Server Sync

Automated access audits start with the `list_kisi_users` and `list_kisi_groups` tools to map exactly who holds physical keys. The agent pulls this directory data to cross-reference against your active employee roster. Stale credentials cause breaches. Your OpenAI Agents SDK MCP Server checks group assignments daily and flags discrepancies. You get a clean report of over-provisioned access without clicking through a web interface.

Remote Door Control Operations

Support tickets for locked-out employees get resolved immediately using the `unlock_kisi_lock` tool. The agent reads the request, verifies the user location via `get_kisi_place`, and triggers the specific hardware. Wait times drop to zero. The system checks `check_kisi_status` to ensure the API is online, validates the employee identity, and fires the command. Handoffs between specialized agents happen automatically if the request hits a restricted zone.

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

Install the package via `pip install openai-agents`. Initialize `MCPServerStreamableHttp` with your endpoint URL. Pass it to the Agent constructor in the `mcp_servers` array, and tools auto-discover immediately.

Yes. Every time the agent calls `unlock_kisi_lock`, the execution trace hits your dashboard. You see the exact payload sent and the latency of the hardware response.

Set `cacheToolsList=True` when configuring your server parameters. This prevents the agent from fetching the schema repeatedly, cutting down latency when running frequent `list_kisi_locks` operations.

The agent catches the failure when calling `check_kisi_status` or any other endpoint. Your guardrails define the fallback behavior, like alerting a human operator instead of retrying blindly.

Your agent processes exact employee names, group IDs, and physical door locations. The managed MCP Server executes these calls securely through the V8 Isolate Sandbox. Tokens remain ephemeral and never leak into model training data.

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