How to Use the Kapwing MCP in Google ADK

Q: How do I connect Google ADK to the Kapwing MCP Server?

You initialize an McpToolset pointing to the Kapwing HTTP server URL and pass it to your LlmAgent tools list. Google ADK handles the transport layer automatically so Gemini can immediately call the rendering functions.

Q: How do I limit Google ADK access to Kapwing tools?

Use the optional toolnames filter when setting up your McpToolset in Python. This lets you restrict the Google ADK agent to only check status with getrenderstatus without giving it permission to generate new video files.

Run enterprise Google ADK agents that process BigQuery data and render videos directly through the Kapwing MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kapwing MCP to Google ADK

Create your Vinkius account to connect Kapwing 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 Kapwing with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Drive Kapwing renders using BigQuery data in Google ADK

The `create_render` tool allows your Google ADK agent to pull structured datasets from BigQuery and transform them into videos. The agent maps database rows to video layers, width, and height before sending them to the Kapwing engine. Gemini's million-token context window lets the agent process massive amounts of raw marketing data at once. It compiles hundreds of personalized video variants and schedules them for rendering without breaking a sweat.

Monitor enterprise renders with Google ADK

The `get_render_status` tool queries Kapwing to track the rendering progress of each video file and fetch the final download link. Your Google ADK agent manages the polling lifecycle, keeping your Vertex AI pipelines updated on job status. If a render takes longer than expected, your agent handles the delay gracefully within its long-running execution loop. You get a reliable way to verify that every video is ready before pushing it to Google Cloud Storage.

Inventory video assets using Google ADK

The `list_renders` tool lists all active and completed video renders inside your account for your Google ADK agent to audit. This allows the agent to keep track of generated video assets and catalog them inside your database. You can configure the MCP toolset to limit exposure if you only want the agent to read historical data. This flexibility keeps your enterprise video automation secure and focused on specific operational tasks.

Setup guide

Set up Kapwing 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 Kapwing 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="Kapwing_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Kapwing 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 Kapwing. 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 Kapwing 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 Kapwing MCP in Google ADK

You initialize an `McpToolset` pointing to the Kapwing HTTP server URL and pass it to your `LlmAgent` tools list. Google ADK handles the transport layer automatically so Gemini can immediately call the rendering functions.

Yes, Gemini's massive context window allows your Google ADK agent to batch multiple `create_render` requests based on BigQuery inputs. The agent coordinates the queue and tracks each render ID to completion.

Use the optional `tool_names` filter when setting up your `McpToolset` in Python. This lets you restrict the Google ADK agent to only check status with `get_render_status` without giving it permission to generate new video files.

Google ADK supports both Stdio and HTTP transports to connect with the MCP Server. For cloud-hosted environments like Vertex AI, the Streamable HTTP transport is the recommended choice for stable connections.

Your video files, JSON templates, and render metadata are processed inside isolated, zero-trust V8 sandboxes. Vinkius secures the MCP communication channel, ensuring your enterprise media assets never leak to external LLM training sets.

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