How to Use the MediaSilo (Legacy) MCP in Pydantic AI

Q: How do I register the MediaSilo (Legacy) MCP Server with a Pydantic AI agent?

Import MCPToolset from the library and initialize it with your server's HTTP URL. Pass this toolset instance inside the toolsets list when instantiating your Agent object.

Build type-safe video review agents using Pydantic AI to validate MediaSilo (Legacy) schemas at runtime.

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 Pydantic AI

Create your Vinkius account to connect MediaSilo (Legacy) to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce strict schemas with Pydantic AI

This MCP Server brings type safety to your legacy video asset pipelines. When your agent calls `get_asset`, Pydantic AI validates the returned metadata fields against strict Python models before your code ever runs. If the legacy API returns unexpected null fields or modified data structures, the system raises a validation error immediately. This prevents corrupted metadata from polluting your downstream video rendering or archiving scripts.

Type-safe project directory audits via MCP Server

Your agent can crawl workspace user directories securely by invoking `list_project_users` to verify project access. The framework validates every user record against a strict schema, ensuring email addresses and user IDs are formatted correctly. It retrieves individual user details using `get_user` to check permissions. If a user record lacks required enterprise fields, your agent catches the mismatch at the boundary instead of failing silently inside a loop.

Secure QuickLink validation inside Pydantic AI

Monitoring external review pages is safer when your agent calls `list_quicklinks` to pull active share links. The framework parses the payload into typed models, verifying expiration formats and access controls. You can inspect a specific link with `get_quicklink` to verify its status. Having runtime validation guarantees that your agent never attempts to process a malformed link object, protecting your review pipelines.

Setup guide

Set up MediaSilo (Legacy) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "mediasilo-legacy-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to MediaSilo (Legacy) tools.",
)

result = await agent.run("List recent MediaSilo (Legacy) transactions")
print(result.output)

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 Pydantic AI

Import `MCPToolset` from the library and initialize it with your server's HTTP URL. Pass this toolset instance inside the `toolsets` list when instantiating your `Agent` object.

The framework will raise a validation error the moment a tool like `list_assets` returns data that violates the schema. This loud failure prevents your agent from making decisions based on malformed or unexpected API structures.

Yes, the toolset is completely model-agnostic. You can hook up tools like `list_projects` and `get_project` to local models running via Ollama or any other supported LLM provider.

Yes, you can connect using either Streamable HTTP or SSE transports. Ensure your hosted server on Vinkius is active and reachable before running your agent script.

All asset metadata, folder structures, and user lists are handled within ephemeral V8 isolates on Vinkius. Your data is processed in-memory and never written to disk, maintaining zero-trust isolation between your agent and the legacy API.

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