How to Use the Trefle MCP in AutoGen

Q: How do I query plant data using Trefle and AutoGen?

You set up a debate where different agents use tools like searchplants and getplant. The conversation forces the models to justify their chosen parameters, leading to a more robust answer than a single tool call.

Q: Can I verify taxonomy using Trefle and AutoGen?

Yes. Agents can challenge each other: Agent A uses getgenus for the broad category, while Agent B verifies details with getspecies. The final decision is a consensus of the most accurate taxonomic data.

Q: What's best practice for getting location data using Trefle and AutoGen?

Let one agent list all available zones via listdistributions. A second agent then takes that full list to call getdistributionplants, ensuring no potential zone is missed during the filtering process.

Get consensus decisions using Trefle data with AutoGen's multi-agent debate framework.

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 AutoGen

Create your Vinkius account to connect Trefle to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debating Botanical Findings

Need to confirm the best plant match? Have one agent use `get_plant` and another agent verify the results using `search_plants`. The agents can then debate which data point is most accurate based on their respective tool inputs. This consensus-driven decision process means you get a verified conclusion, not just the first result from an API call.

Structured Data Validation

Agents can systematically validate data. For instance, one agent calls `get_genus` to establish taxonomy, while another agent uses `list_species` to confirm all belonging species. They challenge each other's assumptions until they reach a consensus on the structure. This structured debate is perfect for high-stakes knowledge management tasks.

Complex Data Filtering and Review

If you need to narrow down plants, one agent can query all zones using `list_distributions`. A second agent then uses the output of that call to filter data via `get_distribution_plants`, effectively refining the search step-by-step. The multiple agents negotiate which combination of parameters yields the most accurate and actionable dataset.

Setup guide

Set up Trefle MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Trefle tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Trefle_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Trefle data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Trefle_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Trefle data")
    print(result.messages[-1].content)

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 AutoGen

You set up a debate where different agents use tools like `search_plants` and `get_plant`. The conversation forces the models to justify their chosen parameters, leading to a more robust answer than a single tool call.

Yes. Agents can challenge each other: Agent A uses `get_genus` for the broad category, while Agent B verifies details with `get_species`. The final decision is a consensus of the most accurate taxonomic data.

Let one agent list all available zones via `list_distributions`. A second agent then takes that full list to call `get_distribution_plants`, ensuring no potential zone is missed during the filtering process.

Yes. You can assign an 'Auditor' agent whose job is solely to check for errors and then use `report_species_error` or `submit_species_correction`. The agents debate the necessary correction before submission.

This MCP Server exposes structured botanical data types: plant names, species records, genus details, and geographical distribution zones. All outputs are text-based JSON structures.

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