How to Use the Cloverly MCP in AutoGen

Q: How to set up Cloverly for AutoGen?

Install the autogen-ext package and use the mcpservertools helper. The adapter automatically maps the server tools to your agents.

Deploy multi-agent teams in AutoGen to debate carbon offset strategies using real-time Cloverly 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 AutoGen

Create your Vinkius account to connect Cloverly 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 Cloverly with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

AutoGen agents debating carbon offsets

Assign one agent to audit spending using `list_purchases` while another proposes new targets. They compare the data to find inefficiencies in your current offset strategy. This negotiation ensures your final decision is vetted. The agents challenge each other's assumptions based on the actual tool output.

Verifying Cloverly estimates with AutoGen

Let a specialized agent call `create_estimate` for a batch of shipments. A second agent then reviews the estimate against your budget constraints. If the estimate exceeds your limit, the agents discuss alternatives. This prevents overspending without requiring you to manually check every transaction.

Managing projects via AutoGen

Use `list_projects` to give your agents a list of available initiatives. They negotiate which projects align with your company's current sustainability goals. They converge on a final selection by comparing `get_project` details. This removes the guesswork from choosing where to invest your carbon credits.

Setup guide

Set up Cloverly 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 Cloverly 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="Cloverly_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

    result = await agent.run("List recent Cloverly 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 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 AutoGen

Install the autogen-ext package and use the mcp_server_tools helper. The adapter automatically maps the server tools to your agents.

Yes. You pass the tool list to the AssistantAgent constructor. This allows multiple agents to perform operations like `get_account` during their collaborative sessions.

Agents use the returned data from the server to argue for specific outcomes. They rely on concrete values rather than general knowledge.

The server supports Streamable HTTP transports. This allows your agents to receive tool results as they are generated, speeding up the debate process.

We use a zero-trust model for agent communication. Your account data is never shared between agents unless they are explicitly authorized by your defined workflow.

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