How to Use the Trefle MCP in Google ADK

Q: How does Trefle help me find plant data using Google ADK?

You use the agent to call tools like searchspecies. The MCP Server executes this query and feeds results directly into your long-context Gemini model for analysis. It keeps everything structured.

Q: Can Trefle handle massive scale data with Google ADK?

Yes. Because the underlying tools, such as listplants, are designed to pull from a massive database, they fit perfectly into the BigQuery and Vertex AI stack you’re using.

Q: What types of queries can Trefle run with Google ADK?

It runs everything from simple lookups (getspecies) to complex distribution analyses using listdistributions. It gives your agent many ways to ask botanical questions.

Q: How does Trefle support data governance on Google ADK?

The MCP Server helps enforce rules by providing tools like submitspeciescorrection, which ensures that any necessary changes are formally logged and processed in the database.

Q: What specific botanical data does Trefle touch with Google ADK?

It primarily touches species records. The function reportspecieserror is specifically designed for flagging issues related to species information within the system.

Build Enterprise Botanical Agents with Google ADK and Trefle MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Trefle MCP to Google ADK

Create your Vinkius account to connect Trefle 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 Trefle with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trefle's Plant Database for Google ADK

The `search_plants` tool lets your agent query the world’s largest botanical database. You can refine searches using filters to narrow down results on main plant species. For deep dives, use `get_plant` after you find a name. The MCP Server ensures that all returned data adheres to enterprise-grade structure for BigQuery ingestion.

Listing and Analyzing Flora with the MCP Server

`list_species` gives your agent a comprehensive list of every species and sub-taxa. Additionally, `list_genera` provides an overview of all available genera. If you need to understand where something grows, call `get_distribution_plants`, passing specific query parameters like the establishment name.

Data Integrity Tools for Google ADK

The agent can maintain data quality by using `report_species_error` when it finds issues. You also have a way to formally update records with `submit_species_correction`. Don't forget you can get general info on a genus using the `get_genus` tool.

Setup guide

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

You use the agent to call tools like `search_species`. The MCP Server executes this query and feeds results directly into your long-context Gemini model for analysis. It keeps everything structured.

Yes. Because the underlying tools, such as `list_plants`, are designed to pull from a massive database, they fit perfectly into the BigQuery and Vertex AI stack you’re using.

It runs everything from simple lookups (`get_species`) to complex distribution analyses using `list_distributions`. It gives your agent many ways to ask botanical questions.

The MCP Server helps enforce rules by providing tools like `submit_species_correction`, which ensures that any necessary changes are formally logged and processed in the database.

It primarily touches species records. The function `report_species_error` is specifically designed for flagging issues related to species information within the system.

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