How to Use the MoeGo MCP in Google ADK

Q: How do I register the MoeGo toolset in Google ADK?

Install the package via pip install google-adk and define your server parameters using StreamableHttpServerParameters. This exposes the MCP tools directly to your LlmAgent to expose tools like listappointments and listcustomers.

Q: Can I limit which MoeGo tools Google ADK can access?

Yes, use the optional toolnames filter when initializing your McpToolset. This allows you to restrict the agent to read-only tools like getpet and block write tools like createappointment.

Q: Can I combine MoeGo reviews with Vertex AI sentiment analysis?

Yes. Your agent can fetch customer feedback using listreviews and pass those strings directly to Vertex AI models to generate sentiment reports or draft personalized email responses.

Q: Where does my pet and customer data go during processing?

Your pet profiles and customer lists accessed via listpets are processed inside isolated V8 sandboxes. This MCP gateway handles the authorization credentials outside the LLM context, encrypting them to ensure zero permanent storage of your operational data.

Connect your MoeGo data to Gemini models using Google ADK to run long-context reasoning over your entire pet care history.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MoeGo MCP to Google ADK

Create your Vinkius account to connect MoeGo 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 MoeGo with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground Gemini reasoning via MoeGo MCP Server

The `list_appointments` tool feeds real-time grooming schedules directly into Gemini's massive context window. Wrapping the toolset in `McpToolset` allows your enterprise agent to analyze weeks of scheduling data at once to find patterns in staff utilization or booking bottlenecks. This setup lets you combine live operational data with your existing Google Cloud resources. The agent runs queries against `list_staff` and matches that information with your cloud-hosted employee records to optimize daily shifts.

Direct BigQuery integration for customer insights

The `list_customers` tool allows your agent to cross-reference CRM data with external databases. This MoeGo MCP Server integrates with Google ADK so you can join customer records with historical marketing tables stored in BigQuery to identify high-value clients. You can also use `list_reviews` to track customer sentiment over time. The agent processes these reviews alongside your business settings from `get_business_settings` to see if pricing updates correlate with changes in customer satisfaction ratings.

Restrict Gemini tool access for security

The `get_pet` tool retrieves sensitive medical and grooming notes for specific animals. Using this MCP Server with the Google ADK `tool_names` filter lets you restrict your agent's access to read-only endpoints like `list_pets` during public-facing customer chats. When building internal tools, you can expose write operations like `create_appointment` only to authenticated staff agents. This keeps your scheduling database safe from accidental modifications while allowing your customer-facing bots to answer basic booking questions.

Setup guide

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

Install the package via `pip install google-adk` and define your server parameters using `StreamableHttpServerParameters`. This exposes the MCP tools directly to your `LlmAgent` to expose tools like `list_appointments` and `list_customers`.

Yes, use the optional `tool_names` filter when initializing your `McpToolset`. This allows you to restrict the agent to read-only tools like `get_pet` and block write tools like `create_appointment`.

Gemini models use their massive token limit to ingest entire lists returned by `list_appointments` and `list_services` simultaneously. This lets the agent analyze complex scheduling conflicts or staff availability trends in a single turn.

Yes. Your agent can fetch customer feedback using `list_reviews` and pass those strings directly to Vertex AI models to generate sentiment reports or draft personalized email responses.

Your pet profiles and customer lists accessed via `list_pets` are processed inside isolated V8 sandboxes. This MCP gateway handles the authorization credentials outside the LLM context, encrypting them to ensure zero permanent storage of your operational data.

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