How to Use the Kling AI (Generative Video & Image) MCP in Google ADK

Q: Is it possible to restrict which Kling AI tools my Google ADK agent can access?

Definitely. When you set up the McpToolset, you can pass a list of tool names to the toolnames argument. This ensures your agent can only see and execute the MCP functions you've explicitly approved.

Connect Kling AI to your Google Cloud data using the long-context reasoning of the Google ADK and Gemini.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kling AI (Generative Video & Image) MCP to Google ADK

Create your Vinkius account to connect Kling AI (Generative Video & Image) 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 Kling AI (Generative Video & Image) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate Video from BigQuery Prompts

The `text_to_video` tool generates a video from a text prompt. Because the Google ADK integrates with your GCP environment, your agent can pull prompts directly from a BigQuery table, generate videos, and then write the final video URLs back to your database. This turns the MCP server into a part of your cloud data pipeline. Your agent starts a job and gets a task ID. It then polls `get_video_task` to check the status. With Gemini's long-context window, your agent can manage hundreds of these tasks at once, keeping track of every ID and its status without losing context.

Animate Your Product Catalog

Use the `image_to_video` tool to bring static product images to life. Your agent can read a list of image URLs from a Google Sheet or Cloud Storage bucket, send them to the Kling AI server for animation, and monitor the progress of each one using `get_video_task`. This is great for creating social media content or product page assets at scale. The Google ADK makes it simple to build agents that operate on your existing cloud data, treating this generative video capability as just another tool in your GCP arsenal.

Filter and Manage Your MCP Toolset

The Kling AI server has ten tools, but your agent might only need two. When you initialize the `McpToolset` in the Google ADK, you can use the `tool_names` filter to expose only the specific functions you want, like `text_to_image` and `get_image_task`. This reduces the agent's attack surface and simplifies its logic. This is a practical way to enforce security and focus your agent on a specific job. You're not just giving it a box of tools; you're handing it the exact two wrenches it needs to get the work done within your Google Cloud environment.

Setup guide

Set up Kling AI (Generative Video & Image) 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 Kling AI (Generative Video & Image) 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="Kling AI (Generative Video & Image)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Kling AI (Generative Video & Image) 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 Kling AI. 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 Kling AI (Generative Video & Image) 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 Kling AI (Generative Video & Image) MCP in Google ADK

The Google ADK is built for this. Your agent can natively access services like BigQuery or Cloud Storage, pull data like text prompts or image URLs, and then pass them to the Kling AI MCP server tools like `text_to_video`.

Gemini's large context window is a major benefit. Your agent can manage a huge list of video generation jobs from `list_video_tasks`, holding all the task IDs and statuses in its context to make smart decisions about what to do next.

Yes. The tools are asynchronous. Your agent can fire off multiple requests to `image_to_video` or `text_to_video`, collect all the task IDs, and then poll their statuses efficiently.

Definitely. When you set up the `McpToolset`, you can pass a list of tool names to the `tool_names` argument. This ensures your agent can only see and execute the MCP functions you've explicitly approved.

The server processes URLs to your media and text prompts you provide. Vinkius ensures all connections are encrypted. When used with Google ADK, your agent's access can be governed by your existing Google Cloud IAM roles, centralizing security management.

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