How to Use the HeyGen MCP in OpenAI Agents SDK

Q: How do I connect HeyGen to the OpenAI Agents SDK?

Run pip install openai-agents and create an MCPServerStreamableHttp instance with your endpoint URL. Pass this MCP server in the mcpservers array to your Agent constructor.

Q: Can the OpenAI Agents SDK find out how many HeyGen credits I have left?

Yes. The agent calls getapiprofile to check your current account limits. You can write a guardrail that stops execution if credits drop below a specific threshold.

Ship production video generation workflows with the OpenAI Agents SDK using this managed MCP connection.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HeyGen MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger Studio Renders via MCP Server

The `generate_video` tool lets your agent construct custom video payloads from scratch. You pass scenes and avatar configurations as a JSON string directly into the API. Your agent calls `list_avatars` beforehand to grab the correct ID, ensuring the chosen presenter matches your brand guidelines exactly. Since you build with OpenAI's guardrails, you can enforce strict validation on the JSON structure before the agent executes the call. If the agent tries to request an avatar that does not exist, the framework catches the error and triggers a handoff to a fallback agent or prompts a human reviewer.

Map Variables to Existing Templates

Use `list_templates` to fetch available video layouts and `get_template_details` to read their variable definitions. Once your agent knows the required fields, it fires `generate_from_template` with a JSON string mapping those variables to actual text. This method runs much faster than building scenes from scratch. You can set up a specialized agent just for template rendering, keeping your tracing logs clean in the OpenAI dashboard. This MCP integration isolates the generation logic from your main reasoning loop.

Polling and Multilingual Processing

Your agent calls `get_video_status` to check on a render and extracts the URL once the endpoint returns completed. This prevents the system from hanging; the agent can do other work while the video processes in the background. Pass an existing video into `translate_video` by defining the configuration in the body. The agent handles the lip-sync instructions automatically based on the target language, letting you scale a single video across multiple regions without manual editing.

Setup guide

Set up HeyGen 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 HeyGen tools at runtime.
3

Create your Agent

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

Run the agent

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

Run `pip install openai-agents` and create an `MCPServerStreamableHttp` instance with your endpoint URL. Pass this MCP server in the `mcp_servers` array to your Agent constructor.

Yes. The agent calls `get_api_profile` to check your current account limits. You can write a guardrail that stops execution if credits drop below a specific threshold.

It exposes a specific endpoint for polling. Your OpenAI agent uses `get_video_status` to monitor the render queue and extracts the final URL when it finishes.

No. The SDK auto-discovers all eleven tools provided by the server. Set `cacheToolsList=True` to speed up the initialization.

The server processes raw JSON strings containing your text variables, scene configurations, and avatar selections. Vinkius runs this in a zero-trust V8 Isolate sandbox, meaning your script payloads are destroyed immediately after the API call completes.

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