How to Use the FileStack MCP in Mastra AI

Q: How do I add FileStack tools to a Mastra AI agent?

Initialize the client using new MCPClient with your Vinkius MCP Server URL. Call mcpClient.listTools() and spread the resulting tools directly into your Mastra agent's tool array.

Q: Can Mastra AI handle FileStack transcoding timeouts?

Yes, Mastra's workflow engine can wrap the getvideostatus polling loop in a retry block. This prevents timeout issues by handling long-running video transcodes in the background.

Q: How do I set up human-in-the-loop for FileStack uploads in Mastra AI?

Use Mastra's requireToolApproval option on the uploadfromurl tool. This pauses the workflow and waits for admin authorization before pulling external files into your system.

Build resilient multi-step media pipelines with Mastra AI and FileStack automation tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FileStack MCP to Mastra AI

Create your Vinkius account to connect FileStack 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 FileStack with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated video transcoding with Mastra AI

The `start_video_transcode` tool starts the conversion process and hands off a tracking UUID to your Mastra AI workflow. Mastra's built-in engine handles the tedious polling loop by calling `get_video_status` with exponential backoff. If a network hiccup occurs, the workflow retries automatically without crashing your pipeline. This setup ensures heavy video files are processed reliably without manual intervention. You write the logic once, and Mastra manages the state machine from upload to final delivery.

Conditional safety moderation workflows

The `get_sfw_status` tool checks uploaded files for explicit content before they reach your database. In Mastra AI, you can build a conditional branch that routes clean images to `get_image_tags` and quarantines unsafe ones. If an image fails the check, Mastra can automatically trigger an alert workflow to notify your team. This prevents bad media from entering your platform. The entire moderation chain runs autonomously, executing complex logic blocks based on the safety score returned by the MCP Server.

Resilient file ingestion pipelines

The `upload_from_url` tool imports files from public web addresses directly into your storage bucket. Your Mastra agent uses this tool to ingest external assets, then immediately chains `get_metadata` to extract file sizes and dimensions. If the source URL is slow or fails, Mastra's workflow engine manages the retry logic. This makes bulk file ingestion resilient against third-party server downtime.

Setup guide

Set up FileStack 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 FileStack 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: "filestack-mcp-client",
  servers: {
    "filestack-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent FileStack 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 Filestack. 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 FileStack 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 FileStack MCP in Mastra AI

Initialize the client using `new MCPClient` with your Vinkius MCP Server URL. Call `mcpClient.listTools()` and spread the resulting tools directly into your Mastra agent's tool array.

Yes, Mastra's workflow engine can wrap the `get_video_status` polling loop in a retry block. This prevents timeout issues by handling long-running video transcodes in the background.

Use Mastra's `requireToolApproval` option on the `upload_from_url` tool. This pauses the workflow and waits for admin authorization before pulling external files into your system.

Yes, the Mastra integration automatically detects whether the MCP Server uses Streamable HTTP or SSE, so you do not need to configure transport protocols manually.

Your credentials and API keys are stored securely in Vinkius, meaning your Mastra workflows never expose raw tokens. All processed media, including images and OCR documents, transit through temporary encrypted memory and are never cached by the MCP Server.

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