How to Use the Brivo MCP in LangChain

Q: Can a LangChain agent automatically release a Brivo door?

Yes, by exposing the unlockdoor tool to your LangChain agent. The agent evaluates your prompt, checks the door's state via getdoorstatus, and executes the tool if the criteria are met.

Q: How do I trace Brivo access event errors in LangChain?

You use LangSmith to monitor the tool calls. When listaccessevents or getuser fails, the exact error payload from the Brivo API is captured in your LangSmith trace.

Build LangChain agents that open doors and track access events on Brivo networks through verifiable tool chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Brivo MCP to LangChain

Create your Vinkius account to connect Brivo 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 Brivo with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Multi-Step Brivo Access Chains in LangChain

This MCP server exposes direct physical security controls like `unlock_door` and `get_door_status` as native LangChain tools. Your agent can evaluate a security incident by first querying `list_access_events` to find suspicious badge swipes and then immediately locking or releasing specific entry points based on the results. You connect these tools directly to your ReAct agent loop, letting LangChain handle the decision-making path. If a user requests entry, the agent checks `get_user` and `list_credentials` before triggering `unlock_door` to grant access.

Trace Physical Security Operations with LangSmith

This MCP server exposes `list_access_events` and `list_access_groups` to pass real-time facility metrics to your LangSmith trace logs. Every call to `unlock_door` flows through your trace dashboard, showing you the exact latency, token usage, and tool arguments. This visibility prevents rogue actions by letting you audit the chain of thought that led to a `list_schedules` lookup. You see the raw inputs and outputs of every Brivo API call directly inside your existing LangChain monitoring stack.

Combine Brivo MCP Server Tools with External DBs

This MCP server connects `list_credentials` and `get_user` to your LangGraph automation pipelines. Your LangChain agent can pull badge IDs, cross-reference them with an HR database, and flag discrepancies using `get_account_info`. By linking these tools inside a single graph, you build workflows that automatically update access permissions. If an employee leaves, the agent matches their record, runs `list_users`, and identifies the exact credentials to revoke.

Setup guide

Set up Brivo 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 Brivo 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({
    "brivo-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 Brivo 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 Brivo. 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 Brivo 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 Brivo MCP in LangChain

You configure the credentials on Vinkius, which hosts the MCP server. Your LangChain code simply initializes the MultiServerMCPClient with the Vinkius endpoint, keeping your API keys out of your application code.

Yes, by exposing the `unlock_door` tool to your LangChain agent. The agent evaluates your prompt, checks the door's state via `get_door_status`, and executes the tool if the criteria are met.

You use LangSmith to monitor the tool calls. When `list_access_events` or `get_user` fails, the exact error payload from the Brivo API is captured in your LangSmith trace.

Install the langchain-mcp-adapters package, initialize the client with your Vinkius HTTP URL, and pass the tools to your agent. This lets you run multi-server aggregation out of the box.

Vinkius runs the server in a zero-trust, sandboxed V8 isolate. Your credential lists and door event logs are processed ephemerally, meaning no physical access data is stored on Vinkius servers after the tool execution completes.

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