How to Use the MediaSilo (Legacy) MCP in OpenAI Agents SDK

Q: How do I initialize the MediaSilo (Legacy) MCP Server within the OpenAI Agents SDK?

Install openai-agents and instantiate the server using MCPServerStreamableHttp. Pass this server instance inside the mcpservers list when creating your Agent object. Set cacheToolsList=True to avoid redundant schema lookups during agent startup.

Q: Can I trace MediaSilo (Legacy) tool calls in the OpenAI developer dashboard?

Yes, every tool invocation like listquicklinks or getproject shows up in your dashboard traces. You can see the exact payload the agent sent and the raw JSON response returned by the server.

Connect your OpenAI Agents SDK builds directly to your video review workspaces to inspect assets and track down active QuickLinks.

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 OpenAI Agents SDK

Create your Vinkius account to connect MediaSilo (Legacy) to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit production assets via the OpenAI Agents SDK

This MediaSilo (Legacy) MCP Server lets your Python agents query video metadata directly inside your production runtimes. Calling `list_assets` pulls your media library into the agent's context, allowing immediate inspection of files without manual dashboard checks. You can route the outputs into other specialized agents using built-in SDK handoffs. If a file looks corrupted or mislabeled, the agent grabs the exact file details with `get_asset` and passes the payload to a cleanup script.

Secure QuickLink tracking with agent guardrails

Your agent inspects active review links by executing `list_quicklinks` to monitor shared video review pages. Because the OpenAI Agents SDK enforces strict runtime guardrails, you can block the agent from sharing sensitive URLs externally. When an approved reviewer requests access, the agent pulls the specific link details via `get_quicklink`. Having these guardrails prevents your agent from accidentally leaking embargoed video files to unauthorized emails.

Map project workspaces and team permissions

Finding who has access to a specific video cut becomes a background task when your agent queries `list_projects` using the MCP Server. Your agent scans active directories and matches them against user permissions using `list_project_users` to verify team assignments. It loops through project lists to find missing team members and flags discrepancies. By running `get_project`, the agent verifies the workspace status before any external creative director gets invited to the review cycle.

Setup guide

Set up MediaSilo (Legacy) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all MediaSilo (Legacy) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives MediaSilo (Legacy) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate MediaSilo (Legacy) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="MediaSilo (Legacy) Agent",
            instructions="You have access to MediaSilo (Legacy) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` and instantiate the server using `MCPServerStreamableHttp`. Pass this server instance inside the `mcp_servers` list when creating your `Agent` object. Set `cacheToolsList=True` to avoid redundant schema lookups during agent startup.

No, this integration focuses entirely on read-only operations to keep your media library safe. Tools like `list_assets` and `get_asset` let your agents read details, but they cannot upload files or change metadata.

This error usually means the authenticated user lacks admin permissions in your MediaSilo (Legacy) workspace. Verify your credentials can access the target project manually, then ensure the agent passes the correct project ID parameter.

Yes, every tool invocation like `list_quicklinks` or `get_project` shows up in your dashboard traces. You can see the exact payload the agent sent and the raw JSON response returned by the server.

Your asset names, project structures, and user lists never transit through third-party databases. The server runs in a secure, isolated V8 sandbox on Vinkius, passing data directly between the legacy API and your local Python runtime.

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