How to Use the Kisi MCP in LangChain

Q: Can my LangChain agent manage multiple Kisi locations at once?

Yes, by using listkisiplaces to get all location IDs first inside your LangChain workflow. Your agent then maps over those IDs, calling listkisilocks for each place to build a complete map of your physical security.

Q: How does LangSmith help me debug Kisi lock operations in LangChain?

LangSmith traces the exact input parameters sent to unlockkisilock or lockdownkisilock inside your chain. You can inspect the JSON payload and the response latency to verify the physical action occurred when expected.

Link physical building security directly to your LangChain runs using this MCP Server so your agent can secure doors on the fly.

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 LangChain

Create your Vinkius account to connect Kisi 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 Kisi with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Security Audits in LangChain

Your agent runs `list_kisi_locks` to map out your entire office layout, stopping you from chasing down physical security logs by hand. It pipes structural data straight into the next link in your run. By combining `list_kisi_users` with LangChain memory, the agent tracks who has access to which doors without making you write custom glue code. It maps out your team's access rights and pipes the results directly into your downstream workflows.

Run Instant Door Lockdowns

This MCP Server triggers `lockdown_kisi_lock` instantly when a threat threshold is crossed in your chain. You no longer have to wait for human intervention during a physical security breach. You can trace the exact latency of the `get_kisi_lock` check in LangSmith to see how fast your system responded. It gives you a clear timeline of the event from the moment the threat was detected to the physical lock confirmation.

Multi-Step Physical Access Pipelines

Before running any physical operations, your agent checks `check_kisi_status` to ensure the MCP Server is responsive. This prevents broken runs when external APIs go down. The output of `get_kisi_user` feeds right into the next step of your LangChain run, letting the agent decide whether to call `unlock_kisi_lock` based on real-time permissions. It turns physical access control into a logical, step-by-step program.

Setup guide

Set up Kisi 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 Kisi 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({
    "kisi-alternative-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 Kisi 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 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 LangChain

You should use standard LangChain exception handling around the tool call. If `check_kisi_status` returns an error, your chain can catch it and route the workflow to an alternative notification step.

Yes, by using `list_kisi_places` to get all location IDs first inside your LangChain workflow. Your agent then maps over those IDs, calling `list_kisi_locks` for each place to build a complete map of your physical security.

LangSmith traces the exact input parameters sent to `unlock_kisi_lock` or `lockdown_kisi_lock` inside your chain. You can inspect the JSON payload and the response latency to verify the physical action occurred when expected.

Filtering the tools array is done before passing it to your LangChain agent. If you only want to allow monitoring, expose `list_kisi_users` and `get_kisi_lock` while keeping the control tools hidden.

Absolutely. All user IDs and lock status payloads are processed in an isolated Vinkius sandbox that destroys all session data the moment your LangChain run finishes. No access logs or credentials are ever stored on our 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