How to Use the ContentGroove MCP in OpenAI Agents SDK

Build production-grade video highlight pipelines with the OpenAI Agents SDK and ContentGroove.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ContentGroove MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate video ingestion in OpenAI Agents SDK pipelines

Kick off your video processing by letting your OpenAI agents ingest files directly. This MCP Server lets your agent trigger `create_media_from_url` to pull footage from any public link, or grab a signed upload URL via `create_direct_upload` when you need to push a raw file straight from your local backend. Because you are running the OpenAI Agents SDK, your agent can automatically pass these upload tasks to a specialized media-handling agent. You get clean tracing on the OpenAI dashboard to watch the exact moment the file handoff occurs and monitor the upload progress.

Track highlight generation with strict guardrails

Stop guessing when your video clips are ready. Your agent can poll `get_media_status` to track processing, then run `get_media_clips` or `list_all_clips` to grab the AI-generated highlight markers the second they are done. The OpenAI framework lets you set up validation guardrails before these tools run. This prevents your agent from requesting clip details on unfinished projects, saving you useless API calls and keeping your token spend in check.

Inspect clip metadata with OpenAI Agents SDK tracing

Deep-dive into specific clips without writing custom parsing glue. Your agent calls `get_clip_details` or `get_media_details` to extract timestamps, transcripts, and highlight scores, giving downstream agents the exact data they need to draft social posts. Since this MCP Server runs inside your SDK pipeline, every metadata request is logged. You can inspect the exact payload returned by the ContentGroove tools directly in your OpenAI run logs, making it easy to debug why a specific highlight was selected.

Setup guide

Set up ContentGroove 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 ContentGroove tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK and initialize the streamable HTTP server using your Vinkius endpoint. Pass this server object in the server list when instantiating your agent, and set the tool list caching to true to keep discovery fast.

Yes, the SDK handles async tool execution natively. Your agent can trigger imports for multiple videos simultaneously while a separate monitor agent checks statuses in the background.

Yes, you can configure a specialized video agent that owns the clip listing tools, then hands off the finalized clip data to a copywriter agent that writes the social media copy.

The server does not ingest the video bytes directly. Instead, your agent calls the direct upload tool to get a secure, signed URL, allowing your client application to upload the raw video file directly to storage.

Your video URLs and clip details are protected. All API calls run through Vinkius's zero-trust sandboxed environment, and this MCP Server ensures your raw video URLs are never exposed or logged outside your specific OpenAI session.

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