How to Use the JumpCloud MCP in Google ADK

Q: How do I set up Google ADK to query my JumpCloud directory?

Install google-adk and initialize McpToolset with your Vinkius HTTP endpoint. Pass this toolset directly to your LlmAgent instance to give Gemini access to this MCP integration.

Q: Can I combine JumpCloud data with BigQuery using Google ADK?

Yes. Your agent can query directory details using listsystems, format the output, and pipe it directly into BigQuery. This makes it easy to build historical compliance dashboards using enterprise SQL tools.

Q: Can I restrict the tools exposed to my Google Cloud agent?

Yes. When initializing McpToolset, you can pass a list of allowed tool names to restrict the agent's scope. For example, you can limit it to listnetworks and block access to user metadata.

Feed your JumpCloud directory metadata directly into Gemini using Google ADK to analyze enterprise-wide system compliance.

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 Google ADK

Create your Vinkius account to connect JumpCloud to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze directory data using Google ADK

Bring your identity data into Gemini's massive context window. By integrating Google ADK with this MCP Server, your enterprise agents can pull complete directory schemas using `list_directories`. This lets you cross-reference active directory configurations, LDAP sources, and Google Workspace integrations in a single reasoning loop. The agent processes thousands of user objects retrieved via `list_users` without hitting token limits. It analyzes account statuses, flags inactive profiles, and correlates this information with your BigQuery HR datasets to find discrepancies.

Correlate device compliance with cloud logs

Keep your physical fleet and cloud infrastructure aligned. The agent uses `list_systems` to pull hostnames, operating systems, and hardware details directly into your Google Cloud environment using our MCP tools. It matches this local machine data against Vertex AI threat models to identify high-risk endpoints. It also queries `list_policies` to verify that active security templates match your enterprise compliance benchmarks. By comparing policy states against raw system logs, the agent spots configuration drift before it causes an incident.

Audit commands and application access

Inspect the scripts running across your machines. Your agent calls `list_commands` to retrieve saved management scripts and analyze their parameters for security risks. It highlights outdated commands that might expose local administrative credentials. It combines this with `list_applications` to map SSO integrations. The agent reviews which SaaS applications are bound to which user groups, ensuring that terminated employees do not retain lingering access through cached application tokens.

Setup guide

Set up JumpCloud MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with JumpCloud tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="JumpCloud_agent",
    model="gemini-2.0-flash",
    instruction="You have access to JumpCloud tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install `google-adk` and initialize `McpToolset` with your Vinkius HTTP endpoint. Pass this toolset directly to your `LlmAgent` instance to give Gemini access to this MCP integration.

Yes. Your agent can query directory details using `list_systems`, format the output, and pipe it directly into BigQuery. This makes it easy to build historical compliance dashboards using enterprise SQL tools.

Gemini's million-token window allows the agent to ingest massive outputs from `list_user_groups` and `list_policies` simultaneously. It can analyze your entire organizational structure in a single pass without pagination bottlenecks.

Yes. When initializing `McpToolset`, you can pass a list of allowed tool names to restrict the agent's scope. For example, you can limit it to `list_networks` and block access to user metadata.

Vinkius executes the MCP Server in an ephemeral, zero-trust V8 sandbox. Your directory metadata, including hostnames, usernames, and security policy names, is only held in memory during the execution of tools like `list_users` and is never logged or cached.

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