How to Use the Kisi MCP in LangChain

Q: How do I track Kisi tool execution latency in LangChain?

LangSmith tracks every call to listlocks or unlockdoor automatically. You get exact millisecond breakdowns of how long the Kisi API took to respond to your agent.

Chain physical building access directly into your LangChain agents to manage doors and users on the fly using this MCP Server.

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

Multi-Step Access Auditing with LangChain

This integration exposes the `list_users` and `list_role_assignments` tools so your LangChain chains can audit who has physical keys to your office. Your agent runs these queries sequentially, checking user IDs against assigned roles to flag drift in real time. It's fast and direct. Because every step is traced in LangSmith, you can see exactly how the agent resolved a user's permissions before deciding whether to flag them. This turns a manual security audit into a self-documenting, automated LangChain run. No manual spreadsheet work required.

Conditional Door Release Chains

The `unlock_door` and `get_lock_details` tools let your LangChain agent inspect a physical entry point and trigger a temporary release based on logic you define. The agent checks the lock status first, verifies the request context, and then fires the open command. By linking these tools inside a ReAct loop, the agent handles failed attempts or offline hardware gracefully without hardcoded scripts. You get a clear, step-by-step log of the decision path in your terminal. Here's the thing: it is completely hands-off.

Location-Aware Facility Management

The `list_places` and `get_place_details` tools give your LangChain agent the physical context it needs to manage multi-site office setups. The agent queries your active locations, groups them by region, and maps out where security policies need updating. Integrating this with an MCP Server means your chains can pull live hardware structures directly into prompt templates. You don't have to hardcode place IDs anymore; the agent finds them dynamically. Period.

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-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

LangSmith tracks every call to `list_locks` or `unlock_door` automatically. You get exact millisecond breakdowns of how long the Kisi API took to respond to your agent.

Yes, you control this by filtering the tool list before passing it to your agent constructor. Simply omit the `unlock_door` tool from the array if you only want the agent to read statuses.

You register the server URL within a MultiServerMCPClient instance alongside other tools. LangChain then aggregates the access control tools with your other APIs in a single agent context.

Use LangChain's built-in retry runnables to wrap the tool calls. If a rapid sequence of `list_users` calls hits a limit, the chain backs off and retries automatically.

This integration handles physical lock IDs, user profiles, and office location coordinates. We run this inside an ephemeral sandbox, meaning no credential logs or access tokens are ever stored on disk.

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