How to Use the Cloutly MCP in Google ADK

Q: How do I install the Cloutly tools in Google ADK?

Install the package using pip install google-adk and initialize McpToolset with your Vinkius URL. Then pass the toolset to your LlmAgent instance.

Q: Can I limit which Cloutly tools my Google ADK agent can access?

Yes, pass a list of allowed tools to the toolnames parameter when creating your McpToolset. This prevents your agent from accessing sensitive endpoints like replytoreview.

Q: How does Cloutly handle long-context review analysis in Google ADK?

The Gemini model ingests thousands of records from listreviews at once. This lets the agent cross-reference customer feedback over months without running out of memory.

Q: Can I trigger review invites based on BigQuery events?

Yes, write a script that queries BigQuery and calls sendreviewinvite through the agent. This automates invites right after a customer purchase is logged.

Q: How secure is my Cloutly business profile data?

Your business profiles and API keys fetched via listbusinesses are isolated in a zero-trust V8 sandbox. This prevents your private business data from being exposed to public training sets.

Connect Cloutly to Google ADK to analyze massive review histories and trigger SMS invites using Gemini.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cloutly MCP to Google ADK

Create your Vinkius account to connect Cloutly 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 Cloutly with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze review trends with Google ADK

The `list_reviews` tool retrieves a list of reviews across connected sources with support for filtering and pagination. Your Gemini agent pulls years of feedback data into its million-token context window to identify recurring service issues. You feed this data directly into BigQuery or Vertex AI using the native Google Cloud integrations. This allows you to combine your public review trends with internal customer databases.

Launch review invites via Google ADK

The `send_review_invite` tool triggers a review request for a customer via Email or SMS. Your enterprise agent runs this tool after detecting a successful delivery event in your Google Cloud database. You initialize this toolset using the MCP configuration and pass it to your `LlmAgent`. By filtering tools with the `tool_names` parameter, you ensure the agent only has access to invite capabilities when authorized.

Manage unanswered feedback with this MCP Server

The `list_pending_reviews` tool retrieves reviews that have not been replied to yet. Your Google ADK agent monitors this list hourly to flag urgent negative reviews that need immediate attention. This setup uses the Streamable HTTP transport to connect your agent to the Vinkius managed endpoint. Your agent can instantly draft context-aware replies based on the specific business profile fetched via `list_businesses`.

Setup guide

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

Install the package using `pip install google-adk` and initialize `McpToolset` with your Vinkius URL. Then pass the toolset to your `LlmAgent` instance.

Yes, pass a list of allowed tools to the `tool_names` parameter when creating your `McpToolset`. This prevents your agent from accessing sensitive endpoints like `reply_to_review`.

The Gemini model ingests thousands of records from `list_reviews` at once. This lets the agent cross-reference customer feedback over months without running out of memory.

Yes, write a script that queries BigQuery and calls `send_review_invite` through the agent. This automates invites right after a customer purchase is logged.

Your business profiles and API keys fetched via `list_businesses` are isolated in a zero-trust V8 sandbox. This prevents your private business data from being exposed to public training sets.

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