How to Use the Cloverly MCP in Google ADK

Q: Can I limit which Cloverly tools are exposed to my Google ADK agent?

Yes. Use the toolnames filter in your McpToolset configuration to expose only read tools like getimpactsummary while blocking purchase tools like createpurchase.

Q: Does this MCP Server support both Stdio and HTTP transports in Google ADK?

Yes. You can connect to Vinkius via the StreamableHttpServerParameters transport, allowing your cloud-deployed Gemini agents to securely communicate with Cloverly over HTTP.

Connect Cloverly to Gemini via Google ADK to analyze and offset your BigQuery shipping data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cloverly MCP to Google ADK

Create your Vinkius account to connect Cloverly 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 Cloverly with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query carbon offset projects in long-context Gemini windows

When your Gemini agent processes massive logistics logs from BigQuery, it needs to match shipments with the right offset projects. This MCP Server lets your agent call `list_projects` to pull a complete list of verified environmental initiatives directly into Gemini's 1M+ token context window. Instead of making multiple API roundtrips, the Google ADK allows the agent to ingest the entire Cloverly project registry. The agent then reasons over project locations, vintage years, and methodologies to select the ideal match.

Automate carbon purchasing with Google ADK and Cloverly

Your enterprise agents running on Google Cloud can trigger carbon offset purchases based on real-time database events. By wrapping this MCP Server in `McpToolset`, your agent gains direct access to `create_purchase` and `get_purchase`. This means a Vertex AI pipeline can detect a completed delivery in your database, calculate the carbon footprint, and immediately execute the offset purchase. No human intervention is required to complete the ledger.

Generate environmental impact reports directly from BigQuery

Pulling sustainability metrics into your corporate dashboard is simple when your agent uses `get_impact_summary` and `get_impact_by_type`. The Google ADK lets your Gemini agent query Cloverly, format the carbon metrics, and write them back to your cloud data warehouse. You can restrict the agent's scope using the ADK's `tool_names` filter. This ensures the agent can only read data with `get_impact_summary` without accidentally triggering purchases.

Setup guide

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

Yes. Use the `tool_names` filter in your `McpToolset` configuration to expose only read tools like `get_impact_summary` while blocking purchase tools like `create_purchase`.

Gemini's long-context window easily ingests the full output of `list_projects` from this MCP Server. The agent can compare dozens of carbon offset projects simultaneously to find the best fit.

Yes. Your agent can monitor BigQuery for new shipping rows, use `create_estimate` to calculate the footprint, and then call `create_purchase` to buy the offset.

Yes. You can connect to Vinkius via the `StreamableHttpServerParameters` transport, allowing your cloud-deployed Gemini agents to securely communicate with Cloverly over HTTP.

Your Cloverly credentials and carbon estimate parameters are isolated within our zero-trust sandbox. No transaction details or shipping weights are stored on Vinkius, ensuring your corporate sustainability data remains secure.

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