How to Use the Cheddar MCP in OpenAI Agents SDK

Q: How do I install the Cheddar tools in OpenAI Agents SDK?

Run pip install openai-agents and initialize MCPServerStreamableHttp with your Vinkius endpoint URL. Pass the resulting server object into the mcpservers list when constructing your agent. The SDK handles tool discovery automatically.

Connect Cheddar to OpenAI Agents SDK to build production billing agents that safely manage subscriptions and track usage.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cheddar MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe billing operations via MCP Server

The Cheddar MCP Server exposes `add_cheddar_charge` directly to your OpenAI Agents SDK setup to handle money without making mistakes. Instead of writing custom API wrappers, your agent reads the tool definition and applies quantity-based charges using built-in guardrails. You define the exact parameters required before the HTTP request executes. Tracing comes standard through the OpenAI dashboard. When a specialized billing agent calls `get_cheddar_customer_details`, you see the exact payload before execution. Handoffs work naturally here. A support agent can verify an account and immediately pass context to a billing agent to process the charge.

Autonomous invoice and transaction auditing

Passing the `list_cheddar_invoices` and `list_cheddar_transactions` tools into your agent constructor lets it pull recent billing history on demand. Agents excel at matching records, but they need raw data first. You set the safety constraints, and the agent cross-references payments against active subscriptions from the MCP Server. Auto-discovery keeps configuration minimal. You initialize the server connection, and OpenAI Agents SDK maps out every endpoint. A routine audit script can wake up, grab the latest transactions, and flag discrepancies without human input.

Dynamic pricing and promotion lookups

By giving your agent access to `list_cheddar_plans` and `list_cheddar_promotions`, it always quotes accurate prices. Hardcoding plan IDs into your prompts breaks the moment marketing runs a sale. The model fetches the active coupons right before generating a response to the customer. Setting `cacheToolsList=True` ensures these lookups happen fast. The agent pulls the core configuration via `get_cheddar_product_info` and caches the tool schemas locally. You get strict execution boundaries combined with real-time pricing data.

Setup guide

Set up Cheddar 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 Cheddar tools at runtime.
3

Create your Agent

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

Run the agent

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

Run `pip install openai-agents` and initialize `MCPServerStreamableHttp` with your Vinkius endpoint URL. Pass the resulting server object into the `mcp_servers` list when constructing your agent. The SDK handles tool discovery automatically.

Yes, the framework includes built-in guardrails for tool execution. When the model attempts to call `add_cheddar_charge`, you can require human approval or run validation logic before the HTTP request fires.

It works natively with the handoff pattern. A general intake agent can use `list_cheddar_customers` to find the account, then transfer execution to a restricted billing agent that has permission to modify the subscription.

Fetching eight different tool schemas on every turn wastes time and tokens. Enabling the cache tells the framework to store the definitions for tools like `list_cheddar_invoices` locally, speeding up the reasoning loop.

Your OpenAI agent communicates through a zero-trust V8 Isolate sandbox. When the agent requests sensitive billing history or customer addresses, the ephemeral server processes the request and instantly terminates. No transaction records persist on Vinkius infrastructure.

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