How to Use the Frame.io MCP in OpenAI Agents SDK

Q: How do I connect Frame.io to the OpenAI Agents SDK?

Install openai-agents via pip. Create an MCPServerStreamableHttp instance with your Frame.io endpoint and pass it to your agent's server list. The SDK handles tool discovery automatically.

Q: Can OpenAI Agents SDK read existing Frame.io comments?

Yes. The agent uses the listassetcomments tool to pull timecoded feedback from any video file. You trace these read operations directly in your OpenAI dashboard.

Build production-ready video review agents with OpenAI Agents SDK and Frame.io.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Frame.io MCP to OpenAI Agents SDK

Create your Vinkius account to connect Frame.io 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 Frame.io with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate QA workflows with OpenAI Agents SDK

Your agent checks the cut. It pulls the active timeline using `list_assets` and `get_asset_details` to verify file specs. If the audio levels peak or the export lacks the requested color grading, it flags the exact timestamp. You do not want a rogue agent spamming the client. Built-in guardrails validate the output before calling `add_comment` or generating new `list_review_links`. The agent hands off the technical summary to a human producer for final approval.

Connect the Frame.io MCP Server to your pipeline

Zero configuration required. You pass the MCP Server endpoint directly to the Agent constructor. The framework auto-discovers the entire toolset. Set `cacheToolsList=True` and your agent immediately knows how to navigate the folder hierarchy with `list_folders` and `list_projects`. It tracks team members via `list_collaborators` without manual mapping.

Track feedback loops across specialized agents

One agent handles audio. Another handles visual effects. They both read from `list_asset_comments` to see what the director already rejected. You track every API call in the OpenAI dashboard. When an agent needs more context, it pulls the original creative brief using `get_project_details`. If billing issues halt production, it checks `list_accounts` and alerts the finance team.

Setup guide

Set up Frame.io 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 Frame.io tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` via pip. Create an `MCPServerStreamableHttp` instance with your Frame.io endpoint and pass it to your agent's server list. The SDK handles tool discovery automatically.

Yes. The agent uses the `list_asset_comments` tool to pull timecoded feedback from any video file. You trace these read operations directly in your OpenAI dashboard.

You configure guardrails in the OpenAI Agents SDK. The framework validates the agent's proposed `add_comment` payload against your safety constraints before executing the API call.

No. The MCP standard exposes the schema automatically. Your agent sees the exact parameters required for endpoints like `get_my_profile` and `list_teams`.

The server accesses video metadata, folder structures, and user profiles. We isolate your session in a V8 sandbox, meaning your project review links and collaborator lists vanish the moment the ephemeral container spins down.

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