How to Use the JumpCloud MCP in LlamaIndex

Q: How can LlamaIndex help me track JumpCloud user changes over time?

You can schedule a script to run listusers daily and index the results. This builds a historical record in your vector store, allowing you to query the state of your JumpCloud users on any given day.

Q: Can I ask my LlamaIndex agent about JumpCloud security policies?

Absolutely. After indexing the output of listpolicies, you can ask questions like "what are the details of the disk encryption policy?". LlamaIndex will retrieve the specific policy data from its knowledge base.

Index your JumpCloud state and query it in natural language with LlamaIndex. Turn your live directory into a knowledge base.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect JumpCloud MCP to LlamaIndex

Create your Vinkius account to connect JumpCloud to LlamaIndex 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 JumpCloud with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a Searchable IT Directory

Stop re-running API calls to check the same thing. With LlamaIndex, you can run `list_users`, `list_systems`, and `list_applications` once, and the results are indexed into a vector store. Now your JumpCloud directory is a searchable knowledge base. This means you can ask questions in plain English, like "show me all systems running macOS" or "which applications does the marketing team use?". LlamaIndex finds the relevant indexed data from past tool calls and gives you a direct answer, grounded in actual state.

RAG for Security & Compliance

Combine your JumpCloud data with your internal security documents. LlamaIndex can build a query engine that uses both. When you ask, "Is our contractor policy being enforced?", it pulls your policy doc and cross-references it with live data from `list_user_groups`. This is how you get answers that are both context-aware and data-driven. The agent isn't just spitting back API output; it's synthesizing information from multiple sources—your docs and your JumpCloud MCP Server—to answer complex compliance questions.

Connect LlamaIndex to JumpCloud

Getting started is quick. You install the `llama-index-tools-mcp` package and point the `BasicMCPClient` at your Vinkius URL. The `McpToolSpec` then wraps the server's tools, like `list_policies` and `list_networks`, making them available to your agent. You can choose which tools to expose to your agent, giving you control over what data gets indexed. This approach turns your live JumpCloud configuration into a queryable resource for any RAG application you build.

Setup guide

Set up JumpCloud MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all JumpCloud MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to JumpCloud tools.",
)
response = await agent.run("List recent JumpCloud data")

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 JumpCloud. 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 JumpCloud 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 JumpCloud MCP in LlamaIndex

You can schedule a script to run `list_users` daily and index the results. This builds a historical record in your vector store, allowing you to query the state of your JumpCloud users on any given day.

Absolutely. After indexing the output of `list_policies`, you can ask questions like "what are the details of the disk encryption policy?". LlamaIndex will retrieve the specific policy data from its knowledge base.

LlamaIndex indexes the API responses. This lets you build a RAG system that can answer questions by searching over historical JumpCloud data, instead of making a new API call for every query.

No. The tools provided by this MCP server are for reading data only. You can use `get_user` to find user details, but you can't create, update, or delete them.

The server only fetches the data your agent requests, like user lists or system configurations. It uses your unique Vinkius token for authentication, and the connection is isolated within Vinkius's ephemeral sandboxes. No credentials are stored.

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