How to Use the HeyGen MCP in Google ADK

Q: How do I install the HeyGen MCP server for Google ADK?

Run pip install google-adk and configure a McpToolset using StreamableHttpServerParameters. Pass this toolset into your LlmAgent initialization.

Q: Can Google ADK see my past generated HeyGen videos?

Yes. The agent calls listvideos to retrieve your generation history. This helps prevent duplicating work if a video was already rendered in a previous session.

Q: Does the agent support custom video scenes with HeyGen?

It does. The generatevideo tool lets Gemini build raw JSON configurations from scratch. You can restrict this by using the toolnames filter if you only want to allow template usage.

Q: How do I track interactive streaming sessions in Google ADK?

Use the liststreaminghistory tool. It returns a log of your past sessions, which Gemini can analyze alongside your other Vertex AI metrics.

Connect Gemini to HeyGen through Google ADK and turn BigQuery data into personalized video campaigns.

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 Google ADK

Create your Vinkius account to connect HeyGen to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render Templates with Google ADK

The `generate_from_template` MCP tool accepts a JSON string mapping text variables to specific fields in a pre-built video layout. Your Gemini agent queries `list_templates` to find the right format, pulls customer data directly from BigQuery, and maps it into the template payload. This approach scales perfectly with long-context models. Gemini can analyze a massive dataset, extract the relevant personalization points, and queue up hundreds of distinct video generation tasks in a single run.

Dynamic Avatar Selection

You use `list_avatars` to fetch the complete catalog of HeyGen presenters, grabbing the required ID for your video configuration. If you need specific categories, `list_avatar_groups` breaks them down so the agent can filter by style or demographic. Before kicking off a massive batch job, the agent hits `get_api_profile`. This confirms you have enough credits to complete the run, preventing Vertex AI from wasting compute cycles on a pipeline that will fail halfway through.

Scale Content Across Languages via MCP Server

The `translate_video` tool takes an existing video and a target language configuration, generating a new version with matched lip-syncing. Gemini can read a user's locale from your GCP database and trigger the translation automatically. To get the final file, the agent polls `get_video_status`. Once the status flips to completed, the tool returns the download URL, which your agent can then write back into your database or push to a Cloud Storage bucket.

Setup guide

Set up HeyGen MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with HeyGen tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="HeyGen_agent",
    model="gemini-2.0-flash",
    instruction="You have access to HeyGen tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Run `pip install google-adk` and configure a `McpToolset` using `StreamableHttpServerParameters`. Pass this toolset into your `LlmAgent` initialization.

Yes. The agent calls `list_videos` to retrieve your generation history. This helps prevent duplicating work if a video was already rendered in a previous session.

It does. The `generate_video` tool lets Gemini build raw JSON configurations from scratch. You can restrict this by using the `tool_names` filter if you only want to allow template usage.

Use the `list_streaming_history` tool. It returns a log of your past sessions, which Gemini can analyze alongside your other Vertex AI metrics.

The server only handles the specific text strings and video configurations you map into the JSON payload. The MCP connection runs through ephemeral, zero-trust sandboxes that wipe all memory the second the request finishes.

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