How to Use the api.video MCP in OpenAI Agents SDK

Q: How do I connect api.video to the OpenAI Agents SDK?

Install the openai-agents package first. Create an MCPServerStreamableHttp instance pointing to your Vinkius endpoint URL. Pass that server object into your Agent constructor's mcpservers array.

Q: Can the OpenAI Agents SDK delete api.video content?

Yes. The deletevideo tool permanently removes encoded media and its associated metadata. You should configure strict guardrails in your agent definition to require human approval before this tool executes.

Q: Does the api.video MCP Server support caching?

You can set cacheToolsList=True when initializing the server connection. This stops the agent from refetching the tool definitions on every single run, which speeds up your deployment.

Give your production OpenAI Agents SDK system direct control over video encoding, hosting, and playback metadata.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect api.video MCP to OpenAI Agents SDK

Create your Vinkius account to connect api.video 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 api.video with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Initialize and Modify Encoded Media

The `create_video_object` and `update_video_details` tools let your OpenAI agent initialize new video streams and modify their metadata. You define the safety constraints in your Python code, and the agent executes the API calls. Setting titles, tags, and descriptions happens through validated handoffs before anything hits the Vinkius MCP Server endpoint. If an agent tries to modify a video that belongs to another customer group, the built-in guardrails catch the unauthorized `update_video_details` request. Dashboard tracing shows exactly which step failed. You get predictable video initialization without worrying about rogue API calls.

Manage Playback States via MCP Server

`get_video_details` and `get_video_analytics` pull performance metrics directly into your agent's context window. Your specialized analytics agent reads playback rates, viewer counts, and device types to figure out which videos need re-encoding. It hands that data off to a reporting agent automatically. This setup pulls raw numbers instead of guessing. When `list_videos` returns an array of tagged content, the OpenAI Agents SDK tracks the exact token usage for that retrieval. You see the complete path from the initial analytics request to the final generated viewer report.

Audit Captions and Branding

`list_video_captions` and `list_video_chapters` expose the internal structure of your hosted media. A dedicated accessibility agent scans every uploaded video to check for missing subtitle tracks. When it finds a gap, the agent flags the video ID for human review. The `list_player_themes` tool also lets the agent verify that custom branding matches your current corporate style guidelines. Everything runs through the async context manager to keep your main thread unblocked.

Setup guide

Set up api.video 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 api.video tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the `openai-agents` package first. Create an `MCPServerStreamableHttp` instance pointing to your Vinkius endpoint URL. Pass that server object into your Agent constructor's `mcp_servers` array.

Yes. The `delete_video` tool permanently removes encoded media and its associated metadata. You should configure strict guardrails in your agent definition to require human approval before this tool executes.

Auto-discovery handles the tool mapping. Your agent reads the MCP Server schema and immediately knows how to call `get_video_analytics` or `create_video_object` without you writing boilerplate API wrappers. Tracing works out of the box.

You can set `cacheToolsList=True` when initializing the server connection. This stops the agent from refetching the tool definitions on every single run, which speeds up your deployment.

This server touches video metadata, viewer analytics, and caption text. Vinkius runs the connection inside a V8 Isolate Sandbox that destroys itself after the agent finishes its task. No data persists in the middle layer.

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