How to Use the Dopplio MCP in Google ADK

Q: How do I initialize the Dopplio MCP Server within Google ADK?

Install the package using pip install google-adk. Define the toolset using McpToolset(serverparams=StreamableHttpServerParameters(url="YOURVINKIUSURL")) and pass it to your LlmAgent using the tools parameter.

Q: How do I limit the Dopplio tools exposed to my Google ADK agent?

Use the optional toolnames filter when initializing your toolset. For example, pass toolnames="generatevideo", "getrenderstatus" to prevent the agent from calling screenshot or list tools.

Feed BigQuery customer data straight into Dopplio video templates using Google ADK to generate personalized outreach at scale.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dopplio MCP to Google ADK

Create your Vinkius account to connect Dopplio 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 Dopplio with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Bulk video personalization using Google ADK

The `generate_video` tool lets your Gemini-powered agent trigger large-scale video personalization jobs directly from your enterprise data sources. Your agent pulls customer profiles from BigQuery, maps them to template variables, and pushes them straight to the rendering queue. Because Gemini models handle long-context reasoning, your agent can process thousands of rows of customer data in a single turn. It matches the correct video template to each recipient's industry without needing custom mapping scripts.

Track batch render jobs with long-context memory

The `list_videos` tool returns a paginated list of all generated clips so your agent can audit active campaigns. Your agent pairs this with `get_render_status` to track progress across large batches without losing state. Since Gemini models hold over a million tokens of context, your agent can keep the entire history of a batch render in its active memory. It instantly spots failed renders and triggers retries for those specific records.

Turn live websites into sales collateral

The `capture_screenshot` tool captures a live image of any URL to generate personalized landing page previews for your target accounts. Your agent feeds these images directly into `render_pdf` to build custom pitch decks on the fly. To set this up, initialize `McpToolset` with your MCP Server URL and pass it to your `LlmAgent` tools list. You can use the `tool_names` filter to expose only the screenshot and PDF tools to your front-end customer agents.

Setup guide

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

Install the package using `pip install google-adk`. Define the toolset using `McpToolset(server_params=StreamableHttpServerParameters(url="YOUR_VINKIUS_URL"))` and pass it to your `LlmAgent` using the `tools` parameter.

Yes, the agent can generate custom HTML strings based on BigQuery data and pass them directly to `render_pdf`. This allows your agent to create highly customized PDFs without hosting external files.

Use the optional `tool_names` filter when initializing your toolset. For example, pass `tool_names=["generate_video", "get_render_status"]` to prevent the agent from calling screenshot or list tools.

Yes, the SDK supports both transport methods. For production workloads running on Google Cloud, HTTP transport via Vinkius MCP endpoints is recommended to handle async video rendering without blocking local resources.

Your video files, HTML templates, and website screenshots are processed in isolated MCP runtimes. Vinkius secures these transactions with zero-trust token authentication, ensuring your target customer data never leaks into public 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