How to Use the CometAPI MCP in OpenAI Agents SDK

Q: How does OpenAI Agents SDK handle model pricing updates from CometAPI?

The agent queries the getpricinginformation tool at runtime to get live rates. This lets your OpenAI Agents SDK dynamically calculate token costs across different backend providers.

Q: How does the CometAPI integration secure my audio files and text prompts?

All audio payloads processed via transcribeaudiototext and text inputs sent to createaichatcompletion run through a zero-trust V8 sandbox on Vinkius. Your API keys and raw media files are never stored or logged on our infrastructure, maintaining strict isolation.

Build guarded, multi-provider AI agents that generate speech, images, and text inside your OpenAI Agents SDK pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CometAPI MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guarded multi-model execution in OpenAI Agents SDK

The CometAPI MCP Server exposes multi-provider text, speech, and image tools directly inside your OpenAI Agents SDK workflow. When your agent calls `create_ai_chat_completion`, the SDK validates the action before hitting the aggregator, keeping your deployment safe. This setup lets you run complex tasks on Claude or Gemini while keeping your master orchestration inside the OpenAI ecosystem.

Convert and transcribe audio on the fly

Handling voice data requires reliable pipelines, and this MCP Server gives your OpenAI Agents SDK the tools to process audio files instantly. Your agent can listen to audio inputs using `transcribe_audio_to_text` and talk back using `convert_text_to_speech`. The OpenAI tracing dashboard captures every single audio conversion step so you never debug blind.

Track multi-provider costs in OpenAI Agents SDK

Running multiple models gets expensive fast, but you can monitor everything directly through this MCP connection. Your agent can call `get_api_usage_statistics` and `get_pricing_information` to check current spending limits before firing off heavy image generation tasks. By letting the agent inspect its own budget, you prevent runaways in production.

Setup guide

Set up CometAPI 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 CometAPI tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package using pip install openai-agents. Then, instantiate MCPServerStreamableHttp pointing to your hosted Vinkius endpoint and pass it into your Agent constructor. Make sure to set cacheToolsList=True so your python agent does not waste time fetching the tool list on every single turn.

Yes, the SDK supports native agent handoffs. You can have one specialized agent handle audio transcription with `transcribe_audio_to_text` and then hand off the clean text to another agent that manages budget tracking.

The agent queries the `get_pricing_information` tool at runtime to get live rates. This lets your OpenAI Agents SDK dynamically calculate token costs across different backend providers.

No, the SDK auto-discovers all ten tools when you pass the server context. Your python code simply imports the agent, connects to the streamable HTTP endpoint, and lets the model select tools like `generate_ai_image` as needed.

All audio payloads processed via `transcribe_audio_to_text` and text inputs sent to `create_ai_chat_completion` run through a zero-trust V8 sandbox on Vinkius. Your API keys and raw media files are never stored or logged on our infrastructure, maintaining strict isolation.

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