How to Use the Cincopa MCP in Google ADK

Q: How does Gemini use Cincopa metadata inside Google ADK via MCP?

Gemini reads the structured JSON output from getassetmetadata directly. Because of the model's large context, it can compare metadata from hundreds of videos to generate detailed performance reports.

Q: How do I handle file uploads through this setup?

Your agent calls getmediauploadurl to obtain a temporary, secure destination link. Your Google Cloud function or backend service then uploads the video file directly to that URL, keeping the agent lightweight.

Connect Cincopa to your Google ADK agents to manage enterprise video databases using Gemini's massive context window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cincopa MCP to Google ADK

Create your Vinkius account to connect Cincopa 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 Cincopa with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze massive video libraries using Google ADK

Feed your entire Cincopa asset catalog into Gemini's million-token context window by calling `list_cincopa_assets`. Your agent gathers metadata for thousands of videos and analyzes them alongside your BigQuery enterprise data without breaking a sweat. The agent uses `get_asset_metadata` to dive deep into specific media files. This lets your Google Cloud pipeline run automated video tagging and performance analysis without hitting context limits.

Enterprise gallery deployment via MCP Server

Create customer-facing video portals directly from your Vertex AI workflows by calling `list_cincopa_templates` to select the right design. Your agent runs `create_new_gallery` to build the media layout instantly. You pass the server parameters using the streamable HTTP setup to handle high-throughput corporate demands. The agent manages the entire setup, matching your cloud database records with live Cincopa galleries.

Automated media cleanup and archiving

Keep your storage costs down by letting Gemini identify obsolete videos using `list_cincopa_galleries` to find inactive pages. The agent runs comparisons against your BigQuery logs and prepares a deletion queue. Once confirmed, the agent calls `delete_media_asset` to purge the files. You can restrict this action by applying a tool filter to your toolset configuration.

Setup guide

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

Initialize the toolset in Python using the SDK's transport parameters pointing to your Vinkius endpoint. Pass this toolset directly to your agent to let Gemini call tools like `list_cincopa_assets`.

Yes, use the optional tool names filter in your toolset configuration. You can expose read-only tools like `get_gallery_details` and completely block access to destructive tools like `delete_media_asset`.

Gemini reads the structured JSON output from `get_asset_metadata` directly. Because of the model's large context, it can compare metadata from hundreds of videos to generate detailed performance reports.

Your agent calls `get_media_upload_url` to obtain a temporary, secure destination link. Your Google Cloud function or backend service then uploads the video file directly to that URL, keeping the agent lightweight.

Vinkius runs this server inside an isolated, ephemeral runtime that destroys session data instantly. Your credentials, temporary upload URLs, and gallery metadata are never written to disk or shared with external LLM logs.

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