How to Use the Cloverly MCP in OpenAI Agents SDK

Q: How do I configure Cloverly tool caching in the OpenAI Agents SDK?

Set cacheToolsList=True when initializing your MCPServerStreamableHttp connection. This stops the SDK from fetching the Cloverly tool schema on every single message turn, saving valuable milliseconds when calculating emissions.

Q: Can my OpenAI Agents SDK system handle multi-agent handoffs for Cloverly calculations?

Yes. You can have one specialized agent run createestimate to calculate shipping emissions, then hand off the context to a purchasing agent that executes createpurchase to buy the corresponding offsets.

Q: Does Cloverly support custom offset projects through the OpenAI Agents SDK?

Absolutely. Your agent can query listprojects to find specific carbon offset initiatives, let the user select one, and then pass that project ID directly into the createpurchase tool call.

Q: How do I handle transaction errors when buying offsets with this MCP Server?

The SDK handles tool failures gracefully. If createpurchase fails due to funding or API issues, the error details are sent back to the agent so it can retry or notify your team.

Buy carbon offsets and calculate shipment emissions directly inside your production OpenAI Agents SDK workflows.

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 OpenAI Agents SDK

Create your Vinkius account to connect Cloverly 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 Cloverly with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Estimate carbon footprints with OpenAI Agents SDK

Your agent can instantly calculate shipping or travel emissions using `create_estimate`. This MCP Server feeds raw transaction data to Cloverly, returning precise metric tons of CO2. Because the OpenAI SDK caches tool definitions with `cacheToolsList=True`, your production agent won't waste latency querying the server schema repeatedly. It just gets the carbon numbers and passes them to the next agent in your pipeline.

Run verified carbon purchases with built-in guardrails

Executing live financial transactions like purchasing carbon offsets requires strict control. This MCP Server exposes `create_purchase` so your agent can buy credits, but the SDK's built-in guardrails ensure the purchase matches exact budget constraints before execution. If an agent tries to buy offsets for a massive shipping route, you can intercept the payload. You verify the parameters against your business logic before Cloverly commits the order and issues the certificate.

Trace carbon impact metrics in your OpenAI dashboard

Tracking the green impact of your operations shouldn't be a guessing game. Use `get_impact_summary` to pull aggregate offset data directly into your agent's context, then watch the execution trace live in your OpenAI dashboard. This setup lets you monitor every call to `list_purchases` or `get_project` without guessing which agent made the call. You get full visibility into how your autonomous system manages carbon accounting.

Setup guide

Set up Cloverly 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 Cloverly tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Cloverly 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="Cloverly Agent",
            instructions="You have access to Cloverly 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 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 OpenAI Agents SDK

Set `cacheToolsList=True` when initializing your `MCPServerStreamableHttp` connection. This stops the SDK from fetching the Cloverly tool schema on every single message turn, saving valuable milliseconds when calculating emissions.

Yes. You can have one specialized agent run `create_estimate` to calculate shipping emissions, then hand off the context to a purchasing agent that executes `create_purchase` to buy the corresponding offsets.

Absolutely. Your agent can query `list_projects` to find specific carbon offset initiatives, let the user select one, and then pass that project ID directly into the `create_purchase` tool call.

The SDK handles tool failures gracefully. If `create_purchase` fails due to funding or API issues, the error details are sent back to the agent so it can retry or notify your team.

Your transaction values, shipping weights, and carbon estimate requests pass through our secure V8 sandbox directly to Cloverly. We never write your API keys or purchase records to persistent storage, keeping your environmental ledger private.

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