How to Use the MediaSilo (Legacy) MCP in Google ADK

Q: How do I configure the MediaSilo (Legacy) MCP Server inside a Google ADK project?

Use McpToolset with StreamableHttpServerParameters pointing to your hosted endpoint. Pass that toolset object into the tools parameter when initializing your LlmAgent.

Q: Can Gemini models in the Google ADK use these tools to modify user accounts?

No, the server only exposes read operations like listusers and getuser. Your Gemini models can audit who has access to your workspaces, but they cannot add, delete, or modify user accounts.

Equip your Google ADK pipelines with direct access to MediaSilo (Legacy) to search video libraries and inspect projects.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MediaSilo (Legacy) MCP to Google ADK

Create your Vinkius account to connect MediaSilo (Legacy) 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 MediaSilo (Legacy) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Process massive video catalogs using Google ADK

This MediaSilo (Legacy) MCP Server connects Gemini's million-token context window to your entire creative library. Your agent runs `list_assets` to pull huge lists of video files directly into its reasoning loop. Because Gemini holds so much information, you can feed the complete output of `list_folder_assets` into a single prompt. The agent then analyzes the folder structure and suggests organization schemes based on your raw asset naming conventions.

Cross-reference BigQuery data with project assets

Your enterprise agents can join external analytics tables with workspace data by running `list_projects`. The agent pulls project records, matches them with performance metrics in Google Cloud, and identifies which creative folders need attention. It retrieves individual workspace parameters using `get_project` to verify matching metadata fields. This lets you build automated reports that highlight underperforming video campaigns directly alongside their active production files.

Automate QuickLink audits across enterprise teams

Security compliance teams can audit shared links by letting the agent invoke `list_quicklinks`. Your Google ADK agent parses the active share links and flags any that have been open for too long. It queries `get_quicklink` to extract expiration dates and recipient emails for suspicious links. This keeps your external review links aligned with your corporate data retention policies without manual spreadsheet tracking.

Setup guide

Set up MediaSilo (Legacy) 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 MediaSilo (Legacy) 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="MediaSilo (Legacy)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to MediaSilo (Legacy) 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 MediaSilo (Legacy). 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 MediaSilo (Legacy) 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 MediaSilo (Legacy) MCP in Google ADK

Use `McpToolset` with `StreamableHttpServerParameters` pointing to your hosted endpoint. Pass that toolset object into the `tools` parameter when initializing your `LlmAgent`.

No, the server only exposes read operations like `list_users` and `get_user`. Your Gemini models can audit who has access to your workspaces, but they cannot add, delete, or modify user accounts.

The tool returns an empty list payload, which your Gemini model will interpret as a folder containing no media. It will not crash your Python script unless you have custom validation that expects items.

Yes, you can restrict which tools the agent can see by passing a list of allowed names to your toolset configuration. This prevents the model from calling tools like `list_quicklinks` if you only want it reading asset metadata.

Your authentication tokens are stored as encrypted environment variables in your Vinkius dashboard. They are injected directly into the isolated sandbox at runtime, ensuring your user directories and project IDs are never exposed to public networks.

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