How to Use the More Trees MCP in AutoGen

Q: How do I register More Trees tools with AutoGen agents?

Use mcpservertools with StreamableHttpServerParams pointing to your Vinkius URL. Pass that list into your AssistantAgent constructor and the schema converts automatically.

Deploy AutoGen multi-agent teams that debate, verify, and execute More Trees planting campaigns based on corporate rules.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect More Trees MCP to AutoGen

Create your Vinkius account to connect More Trees 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 More Trees with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute audited planting with AutoGen

The `plant_trees` tool becomes an action that your agents must negotiate before executing. A finance agent reviews the budget while a sustainability agent pushes for higher offset volumes. They converse until they reach a consensus that fits your parameters. Once agreed, the execution agent fires the tool and immediately runs `check_moretrees_status` to ensure the API accepted the request.

Cross-verify environmental impact

Calling the `get_impact_report` tool gives your analyst agent the raw numbers needed for a quarterly review. Another agent acting as a compliance auditor challenges those numbers by requesting the underlying logs. The auditor agent runs `list_transactions` to check the math. If the totals match the reported impact, the team outputs a finalized summary for human review.

Debate project selection via MCP Server

Choosing where to plant requires balancing cost against ecological value. Your research agent uses `list_projects` and `get_forest` to pull the specifics of different global initiatives. The team debates the merits of each location based on the retrieved data. They finalize the best option and automatically pull the proof via `get_certificate` once the transaction clears.

Setup guide

Set up More Trees 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 More Trees 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="More Trees_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent More Trees 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="More Trees_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent More Trees 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 More Trees. 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 More Trees 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 More Trees MCP in AutoGen

Use `mcp_server_tools` with `StreamableHttpServerParams` pointing to your Vinkius URL. Pass that list into your `AssistantAgent` constructor and the schema converts automatically.

They share the tool list, but execution happens sequentially based on the conversation turn. One agent proposes calling `get_planting_status`, and the designated executor runs it.

You introduce a human-in-the-loop agent or set strict volume caps in the system prompt. The agents must get explicit approval before invoking the planting function.

Yes. The framework handles Streamable HTTP transports natively. Your agents see the data from `get_project` as it arrives.

The server processes your account IDs and planting logs only for the duration of the request. Vinkius enforces a zero-trust architecture, meaning your financial offset records vanish the second the session closes.

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