How to Use the Jamf Pro MCP in LangChain

Q: Can LangChain run multi-step audits using the Jamf Pro MCP Server?

Yes, you can build chains where the agent first calls listcomputers to find unencrypted Macs, and then automatically loops through getcomputer for each matching ID. LangSmith tracks every tool execution so you can monitor API latency and token usage.

Let your LangChain agents run multi-step Apple device audits and chain Jamf Pro inventory checks without manual scripting.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jamf Pro MCP to LangChain

Create your Vinkius account to connect Jamf Pro 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 Jamf Pro with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain device lookups with LangChain

The `get_computer` tool exposes deep hardware details, disk encryption status, and installed apps directly to your reasoning chains. When your agent runs, it can feed the output of `list_computers` into a second step that pulls specific profiles. LangChain coordinates this sequence, passing serial numbers from the initial list directly into detailed security audits without hardcoded scripts.

Audit mobile security status sequentially

The `get_mobile_device` tool retrieves OS versions and security compliance states for individual iOS or iPadOS assets. Your LangGraph pipelines can evaluate this data to trigger downstream alerts. If `list_mobile_devices` flags an unmanaged device, the chain immediately pulls its full record to verify user assignment before opening an IT ticket.

Map organizational metadata in MCP Server chains

The `list_departments` tool provides the structural hierarchy of your business units to help categorize device distribution. By combining this with `list_buildings` and `list_users`, your agent maps exactly where hardware sits. LangSmith traces these multi-step metadata queries, showing you the exact inputs and outputs of each Jamf Pro API call.

Setup guide

Set up Jamf Pro 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 Jamf Pro 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({
    "jamf-pro-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 Jamf Pro 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 Jamf Pro. 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 Jamf Pro 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 Jamf Pro MCP in LangChain

Look, you don't need to pass raw credentials to your agent. Vinkius manages the Jamf Pro API authentication securely, exposing a single endpoint token that you initialize inside your MultiServerMCPClient setup.

Yes, you can build chains where the agent first calls `list_computers` to find unencrypted Macs, and then automatically loops through `get_computer` for each matching ID. LangSmith tracks every tool execution so you can monitor API latency and token usage.

Here's the thing: the server executes inside a sandboxed V8 isolate that optimizes request headers to prevent rate-limiting during heavy loops. If your chain calls `list_mobile_devices` repeatedly, the managed endpoint handles the connection overhead cleanly.

Absolutely. You can register this MCP server alongside other tools in your LangChain agent, allowing it to fetch Mac data and cross-reference it with your internal databases in one run.

Your Jamf Pro serial numbers, user assignments, and disk encryption statuses are never stored or logged by Vinkius. The MCP execution environment is completely ephemeral, meaning all device data passes through memory and vanishes the millisecond the API request finishes.

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