How to Use the MediaSilo MCP in Mastra AI

Q: How does Mastra AI handle rate limits when calling MediaSilo?

Mastra uses automatic retries with exponential backoff. If listassets hits a rate limit, the client pauses and retries the request without crashing your active workflow.

Q: Can I build multi-step video automation using Mastra AI and MediaSilo?

Yes. You can chain tools like listprojects to find active jobs, then feed those IDs into getprojectassets to audit files, all within a single TypeScript agent.

Q: How do I register the MediaSilo MCP tools in my Mastra AI agent?

Initialize the client with your server URL, call mcpClient.listTools(), and spread the tools into your agent config. It automatically configures transport protocols.

Q: What happens if a specific asset lookup fails during a workflow?

Your agent can catch the error from getasset and branch to an alternate path, like searching for a similar file with searchassets before giving up.

Build resilient, automated video workflows with Mastra AI and the MediaSilo integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MediaSilo MCP to Mastra AI

Create your Vinkius account to connect MediaSilo to Mastra 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 with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate review link distribution with Mastra AI

When a new cut lands, you shouldn't have to manually email clients. Use this MCP Server to trigger a workflow that calls `list_quicklinks` and `get_quicklink` whenever a project updates. If a link fails to generate, Mastra's built-in retry logic kicks in automatically. It backs off, tries again, and only pings your team if the platform itself is down.

Conditional project tracking and asset audits

Keeping track of assets across hundreds of folders is a chore. This MCP Server integration lets you build workflows that run `list_projects` and iterate through files using `get_project_assets` to flag missing metadata. You can set up conditional branches: if a video lacks a description, the agent runs `list_users` to find the owner and logs a task. It keeps your library clean without manual checking.

Run human-in-the-loop approvals for video shares

You don't want an agent sharing rough cuts with clients by mistake. Mastra lets you require approval before the MCP agent calls `get_quicklink` to distribute a link. The system pauses the workflow, alerts your producer, and waits for a green light. Once approved, it fetches the link and wraps up the task.

Setup guide

Set up MediaSilo MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All MediaSilo tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "mediasilo-mcp-client",
  servers: {
    "mediasilo-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "MediaSilo Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to MediaSilo tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent MediaSilo transactions"
);
console.log(result.text);

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. 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 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 MCP in Mastra AI

Mastra uses automatic retries with exponential backoff. If `list_assets` hits a rate limit, the client pauses and retries the request without crashing your active workflow.

Yes. You can chain tools like `list_projects` to find active jobs, then feed those IDs into `get_project_assets` to audit files, all within a single TypeScript agent.

Initialize the client with your server URL, call `mcpClient.listTools()`, and spread the tools into your agent config. It automatically configures transport protocols.

Your agent can catch the error from `get_asset` and branch to an alternate path, like searching for a similar file with `search_assets` before giving up.

Yes. Your API keys and project structures run in a zero-trust environment. The MCP server only handles the specific video titles and project IDs required to execute your workflow steps.

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