How to Use the D-ID MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK manage D-ID credit budgets?

Yes. Your agent can query getcredits before starting a run. You can write custom guardrails in Python to halt the pipeline if your balance falls below a specific threshold.

Q: Does the OpenAI Agents SDK support custom avatars with D-ID?

Yes, it does. Your agent can call uploadimage to send a face photo, then use that image URL inside createtalk to generate a custom talking video.

Q: How do we handle long-running video generation tasks?

Use gettalk to poll the status of the video. The agent checks if the status is finished, then retrieves the final video URL once the render completes.

Build production-grade agents that generate D-ID talking avatar videos using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect D-ID MCP to OpenAI Agents SDK

Create your Vinkius account to connect D-ID 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 D-ID with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate video clips with OpenAI Agents SDK

Your python agents can spin up video presenters on demand. Call `create_clip` to spawn a digital human with a stock background, then track its progress using `get_clip`. The SDK handles the heavy lifting, letting your agent monitor the process until the video is ready. This means your production pipeline gets a raw video URL without manual intervention.

Voice-to-video pipelines via MCP Server

This MCP Server lets you feed raw audio files directly into your video generation pipeline. The agent uses `create_talk_audio` to map voice tracks to avatar lip movements, making the output look natural. You can upload custom face images with `upload_image` to personalize the presenter. If a generation goes wrong or you need to clean up, the agent triggers `delete_talk` to keep your workspace tidy.

Guardrails for D-ID video generation

Avoid burning through your budget on runaway loops. Your agent checks the current balance using `get_credits` before initiating any rendering tasks. You run `list_presenters` to fetch valid IDs before calling `create_talk`. This validation step prevents invalid API calls, keeping your production logs clean and your costs predictable.

Setup guide

Set up D-ID 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 D-ID tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package using pip, then instantiate MCPServerStreamableHttp with your Vinkius endpoint. Pass this server instance into your Agent constructor to let the agent auto-discover the video tools.

Yes. Your agent can query `get_credits` before starting a run. You can write custom guardrails in Python to halt the pipeline if your balance falls below a specific threshold.

Yes, it does. Your agent can call `upload_image` to send a face photo, then use that image URL inside `create_talk` to generate a custom talking video.

Use `get_talk` to poll the status of the video. The agent checks if the status is finished, then retrieves the final video URL once the render completes.

Your uploaded face images and audio tracks are processed in a zero-trust V8 sandbox on Vinkius. Files are sent securely to the video API and are not stored permanently on our intermediate servers.

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