How to Use the Spiritme MCP in OpenAI Agents SDK

Q: How do I check the connectivity of Spiritme with the OpenAI Agents SDK?

You call checkspiritmestatus. This immediately verifies that all connections are active, letting your agent know right away if it needs to pause or try a different endpoint.

Q: Can I delete videos created by Spiritme using the OpenAI Agents SDK?

Yes. If you need to clean up assets, deletevideo handles that job. You simply provide the video ID and it takes care of removing the content from the system.

Q: What is the best way to list templates with Spiritme using the OpenAI Agents SDK?

Just use listtemplates. This function pulls a clean list of all available video formats. It's helpful for your agent because it gives you options before you try to build anything.

Q: Does Spiritme support generating audio files with the OpenAI Agents SDK?

It does. The generateaudio tool lets you create standalone sound files. This is useful if your agent needs just a voice track, without needing to render an entire video.

Q: What data privacy assurances are provided when using Spiritme and the OpenAI Agents SDK?

The MCP Server handles video metadata. The system confirms that only necessary job and asset identifiers are logged for processing, keeping your content details private.

Create personalized videos using the OpenAI Agents SDK. Production-ready content generation, guaranteed.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Spiritme MCP to OpenAI Agents SDK

Create your Vinkius account to connect Spiritme to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Spiritme with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Generate high-quality marketing videos.

You can generate full video campaigns that feature digital human presenters delivering custom scripts. The primary function is `generate_video`, which takes inputs like the desired template and specific voice to build out the final asset. It’s not just a simple API call; you control the whole process using tools like `get_template` and `list_voices`. You'll send data through, watch it happen, and get back finished videos that fit your campaign needs.

Manage digital human assets.

The MCP Server gives you full control over the presenters themselves. Use `get_avatar` to pull specific avatar details or `list_avatars` to see everything available in your library. This lets your agents select the perfect face and style for any given message. Don't forget about audio components either. You can get voice details with `get_voice` or check out all available options by running `list_voices`. It’s all part of keeping your content consistent.

Monitor complex job status.

Video generation isn't instant. The system runs in the background, so you need to know what stage the video is in. Use `get_job_status` to check if a render finished or if it's still processing. This tool keeps your entire agent workflow moving forward without hanging. If something goes wrong, you can use `check_spiritme_status` first to make sure the whole system is up and running. Knowing the status lets your production agents handle retries correctly.

Setup guide

Set up Spiritme 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 Spiritme tools at runtime.
3

Create your Agent

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

Run the agent

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

You call `check_spiritme_status`. This immediately verifies that all connections are active, letting your agent know right away if it needs to pause or try a different endpoint.

Yes. If you need to clean up assets, `delete_video` handles that job. You simply provide the video ID and it takes care of removing the content from the system.

Just use `list_templates`. This function pulls a clean list of all available video formats. It's helpful for your agent because it gives you options before you try to build anything.

It does. The `generate_audio` tool lets you create standalone sound files. This is useful if your agent needs just a voice track, without needing to render an entire video.

The MCP Server handles `video metadata`. The system confirms that only necessary job and asset identifiers are logged for processing, keeping your content details 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