How to Use the FileStack MCP in OpenAI Agents SDK

Q: How do I handle FileStack file uploads inside the OpenAI Agents SDK?

You run uploadfromurl to ingest the file directly to FileStack storage. The tool returns a clean handle that your OpenAI Agents SDK can immediately pass to other tools.

Q: Can my OpenAI Agents SDK verify image safety with FileStack?

Yes, by calling getsfwstatus through the FileStack MCP Server. Your agent inspects the safety score first and can trigger a handoff to a human moderator if the file fails the check.

Q: Does this integration support video transcoding?

Yes, it uses startvideotranscode to initiate async processing. Your agent gets a UUID back and can check the progress later using getvideostatus.

Q: How do I configure the FileStack MCP Server with OpenAI Agents SDK?

Initialize MCPServerStreamableHttp pointing to your Vinkius endpoint and pass it in the mcpservers list. The OpenAI Agents SDK auto-discovers all eight tools, including generatetransformurl.

Run safe, production-grade file transformations and OCR directly inside your OpenAI Agents SDK workflows.

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 OpenAI Agents SDK

Create your Vinkius account to connect FileStack 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 FileStack with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe file ingestion for OpenAI Agents SDK

Your OpenAI agents can ingest external files safely by calling `upload_from_url` to pull assets directly into FileStack storage. This keeps untrusted URLs out of your core Python runtime while letting your agent inspect the file structure. Once uploaded, the agent uses `get_metadata` to grab EXIF data and file properties. This metadata feeds directly into the OpenAI tracing dashboard, so you can track exactly what files your production agents are processing.

Computer vision and OCR guardrails

Prevent your agents from processing toxic files by chaining `get_sfw_status` before any downstream analysis runs. This MCP Server lets your OpenAI Agents SDK configuration block unsafe images automatically, saving API credits and protecting your brand. For clean assets, the agent calls `get_ocr` to extract raw text or `get_image_tags` to identify objects. This structured visual data is returned directly to the agent's context window, allowing for immediate reasoning without custom raw vision pipelines.

Asynchronous video pipelines

Triggering `start_video_transcode` inside an OpenAI agent lets you offload heavy video processing to FileStack without causing timeouts. The agent receives a clean UUID to track progress without blocking the main execution thread. The agent then polls `get_video_status` during its execution loop to determine when the asset is ready. You can also build a transformation pipeline by generating secure delivery links with `generate_transform_url` once transcoding finishes.

Setup guide

Set up FileStack 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 FileStack tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate FileStack 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="FileStack Agent",
            instructions="You have access to FileStack 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 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 OpenAI Agents SDK

You run `upload_from_url` to ingest the file directly to FileStack storage. The tool returns a clean handle that your OpenAI Agents SDK can immediately pass to other tools.

Yes, by calling `get_sfw_status` through the FileStack MCP Server. Your agent inspects the safety score first and can trigger a handoff to a human moderator if the file fails the check.

Yes, it uses `start_video_transcode` to initiate async processing. Your agent gets a UUID back and can check the progress later using `get_video_status`.

Initialize `MCPServerStreamableHttp` pointing to your Vinkius endpoint and pass it in the `mcp_servers` list. The OpenAI Agents SDK auto-discovers all eight tools, including `generate_transform_url`.

All files, images, and videos are processed in Vinkius's zero-trust sandboxed environment. FileStack handles the storage and transcoding, meaning your raw OCR text and media metadata never persist in the MCP runtime after the tool execution completes.

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