How to Use the Trefle MCP in OpenAI Agents SDK

Q: How do I find data on specific plants using Trefle and OpenAI Agents SDK?

You start by calling searchplants. This tool lets your agent search the main plant records, giving you a list of results immediately. The MCP Server then provides all the details for those matching entries.

Build Production Botanical Agents with OpenAI Agents SDK 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 OpenAI Agents SDK

Create your Vinkius account to connect Trefle to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search Plant Data with the Trefle MCP Server

You can search through main plants using `search_plants` or check all species via `search_species`. This makes it easy to find specific flora without knowing its full classification. The server lets you get detailed info on a single plant (`get_plant`) or drill down into the details of a genus (`get_genus`). It’s perfect for agents that need reliable, structured data.

Managing Species and Distribution

Need to update some records? Use `submit_species_correction` if you find bad data, or run the agent through `report_species_error`. You can also list all major zones using `list_distributions`. When tracking flora across regions, call `get_distribution_plants`, filtering by establishment like 'native' to pinpoint exact locations.

Listing and Exploring Botanical Categories

`list_species` gives you a complete rundown of every species and sub-taxa. You can also get an overview of all available genera using `list_genera`. If your job is just to see what's out there, call `list_plants` for a list of main plant types, excluding varieties or subspecies.

Setup guide

Set up Trefle MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Trefle tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Trefle tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Trefle tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Trefle Agent",
            instructions="You have access to Trefle tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You start by calling `search_plants`. This tool lets your agent search the main plant records, giving you a list of results immediately. The MCP Server then provides all the details for those matching entries.

Yes. If an agent finds outdated or incorrect species information, it can use `submit_species_correction`. This tool submits a formal data correction request directly to the botanical database.

The MCP Server covers plants, species, and genera. You can use `get_species` for detailed information on a specific type, or use `list_genera` to see all major groups.

Absolutely. The MCP Server is designed for production environments. Your agent can rely on the structured output of tools like `get_plant`, knowing it's built to handle real-world, mission-critical data.

The server handles species data. Specifically, it manages the submission and correction of species information via `submit_species_correction`.

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