How do I start a video upload?

Use the `create_video_upload` tool, which will create the asset in your specified collection and provide a temporary `upload_url` for your file.

Can I update the thumbnail for a video already uploaded?

Yes! The `update_video_thumbnail` tool allows you to specify a time offset in seconds. Gumlet will extract that specific frame and set it as the new thumbnail.

Does it support viewing stats and bandwidth usage?

The `get_video_analytics` tool provides detailed viewing metrics and bandwidth consumption data for any video ID in your account.

INSTANT PLUG AND PLAY

Gumlet MCP Server for OpenAI Agents SDKGive OpenAI Agents SDK instant access to 12 tools to Create Collection, Create Video Upload, Delete Video, and more

Name: Gumlet
Availability: InStock
Author: Vinkius

Built by Vinkius GDPR 12 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Gumlet through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Use with Your AI Agent

Ask AI about this App Connector for OpenAI Agents SDK

Open in ChatGPT Open in Claude Open in Perplexity

The Gumlet app connector for OpenAI Agents SDK is a standout in the Image Video category — giving your AI agent 12 tools to work with, ready to go from day one.

Vinkius delivers Streamable HTTP and SSE to any MCP client

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Gumlet Assistant",
            instructions=(
                "You help users interact with Gumlet. "
                "You have access to 12 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Gumlet"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Gumlet MCP Server

Connect your Gumlet account to any AI agent and take full control of your video hosting and image optimization workflows through natural conversation.

The OpenAI Agents SDK auto-discovers all 12 tools from Gumlet through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Gumlet, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Video Lifecycle — Manage the complete video lifecycle from creating new uploads and retrieving metadata to monitoring transcoding status
Media Organization — Create and manage collections/folders programmatically to maintain a structured media library
Visual Control — Automate thumbnail updates by selecting specific video frames or time offsets for perfect visual representation
Optimization Insights — Monitor real-time video analytics, viewing metrics, and bandwidth usage for every asset in your account
Image Source Management — List and manage image optimization sources and organization users to ensure high-fidelity delivery

The Gumlet MCP Server exposes 12 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

All 12 Gumlet tools available for OpenAI Agents SDK

When OpenAI Agents SDK connects to Gumlet through Vinkius, your AI agent gets direct access to every tool listed below — spanning video-hosting, image-optimization, cdn-delivery, and more. Every call is secured with network, filesystem, subprocess, and code evaluation entitlements inside a sandboxed runtime. Beyond a simple connection, you get a full AI Gateway with real-time visibility into agent activity, enterprise governance, and optimized token usage.

create_collection

Add new folder

create_video_upload

Upload new video

delete_video

Remove video asset

get_account_info

Get profile details

get_video_analytics

Check video stats

get_video_details

Check video status

list_image_sources

List image optimized sources

list_org_users

List team members

list_video_collections

List folders

list_videos

List video assets

list_webhooks

Get active webhooks

update_video_thumbnail

Set thumbnail offset

Connect Gumlet to OpenAI Agents SDK via MCP

Follow these steps to wire Gumlet into OpenAI Agents SDK. The entire setup takes under two minutes — your credentials stay safe behind the Vinkius.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 12 tools from Gumlet

Why Use OpenAI Agents SDK with the Gumlet MCP Server

OpenAI Agents SDK provides unique advantages when paired with Gumlet through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Gumlet + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Gumlet MCP Server delivers measurable value.

Automated workflows: build agents that query Gumlet, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Gumlet, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Gumlet tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Gumlet to resolve tickets, look up records, and update statuses without human intervention

Example Prompts for Gumlet in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Gumlet immediately.

"Create a new video upload in collection 'col_123' titled 'Annual Report 2026'."

"Check the transcoding status of video 'asset_987'."

"Show me the viewing stats for my latest product video."

Troubleshooting Gumlet MCP Server with OpenAI Agents SDK

Common issues when connecting Gumlet to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Gumlet + OpenAI Agents SDK FAQ

Common questions about integrating Gumlet MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.

Can I use multiple MCP servers in one agent?

Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.

Does the SDK support streaming responses?

Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.