How to Use the Atlas MCP in Google ADK

Q: How do I load Atlas tools into a Google ADK agent?

Initialize the Google ADK McpToolset with your Vinkius HTTP endpoint URL for Atlas. Pass this toolset directly into the Google ADK LlmAgent constructor to expose the Atlas ticketing tools.

Q: Can I filter which Atlas tools are exposed to Google ADK?

Yes, the Google ADK McpToolset constructor accepts an optional list of Atlas tool names. You can restrict your Google ADK agent to reading articles with listarticles while blocking createticket.

Q: Is my Atlas customer data safe when using Google ADK?

Every Google ADK request to listcustomers runs inside an isolated, zero-trust network boundary. Your Atlas customer records are transmitted securely via the MCP connection and are never used to train Google ADK models.

Run enterprise support agents on Google ADK with direct access to Atlas tickets and customer profiles.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Atlas MCP to Google ADK

Create your Vinkius account to connect Atlas 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 Atlas with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Context-rich ticket analysis using Google ADK

The `list_tickets` tool pulls historical support data directly into your Gemini model's million-token context window. This massive context capacity lets your Google ADK agent analyze thousands of previous Atlas conversations to find patterns. Instead of searching blindly, the Google ADK agent uses `get_ticket` to pull specific Atlas threads and compare them against BigQuery tables. You get deep analysis of recurring Atlas support issues without hitting Gemini context limits.

Build Google Cloud agents with the Atlas MCP Server

The `get_customer` tool connects your Atlas CRM data with the Google ADK agent ecosystem. By exposing this tool through an MCP configuration, your Google ADK agents can cross-reference Atlas profiles with BigQuery. Your Google ADK agent uses `list_customers` to find matching records, then feeds that structured Atlas data into your Vertex AI pipelines. This setup lets you automate complex enterprise support workflows in Google Cloud based on the Atlas customer tier.

Automate agent routing using team lists

The `list_users` tool exposes your Atlas agent directory to the Google ADK runtime. Your Google ADK agent checks who is online and active in Atlas before assigning or routing a critical customer issue. If a high-priority Atlas ticket comes in, the Google ADK agent runs `get_account_check` to confirm the pipeline is active. The Google ADK agent then identifies the right human agent in Atlas and prepares the ticket handoff.

Setup guide

Set up Atlas 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 Atlas 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="Atlas_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Atlas 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 Atlas. 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 Atlas 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 Atlas MCP in Google ADK

Initialize the Google ADK `McpToolset` with your Vinkius HTTP endpoint URL for Atlas. Pass this toolset directly into the Google ADK `LlmAgent` constructor to expose the Atlas ticketing tools.

Yes, the Google ADK `McpToolset` constructor accepts an optional list of Atlas tool names. You can restrict your Google ADK agent to reading articles with `list_articles` while blocking `create_ticket`.

Gemini models in Google ADK handle large payloads easily, so you can feed the entire output of Atlas `list_tickets` into the prompt. The Google ADK model processes the raw Atlas JSON without needing aggressive truncation.

No, Vinkius hosts the Atlas server in a secure cloud environment. Your Google ADK code connects directly to the hosted HTTP endpoint, eliminating local Atlas MCP runtime dependencies.

Every Google ADK request to `list_customers` runs inside an isolated, zero-trust network boundary. Your Atlas customer records are transmitted securely via the MCP connection and are never used to train Google ADK models.

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