How to Use the Frame.io MCP in Google ADK

Q: How do I initialize Frame.io tools in Google ADK?

Install google-adk and create an McpToolset using your server URL. Pass this toolset into your LlmAgent constructor. The Gemini model immediately understands how to call the endpoints.

Q: Can Google ADK restrict which Frame.io tools the agent uses?

Yes. You pass a toolnames filter when setting up the McpToolset. This prevents the agent from calling addcomment if you only want it reading data via listassets.

Q: Does Google ADK work with long Frame.io comment threads?

It does. You pull thousands of comments using listassetcomments across multiple projects. Gemini processes the entire batch to identify recurring feedback trends.

Give your Google ADK agents direct access to Frame.io video assets and comments.

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 Google ADK

Create your Vinkius account to connect Frame.io to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed entire project histories to Google ADK

Gemini handles massive context windows. You dump the results of `list_asset_comments` and `get_project_details` straight into the prompt. The agent reads every piece of feedback across a hundred video cuts at once. It cross-references those comments against your production data in BigQuery. When a client asks why a specific shot changed, the agent pulls the exact `list_review_links` and explains the revision history.

Deploy the Frame.io MCP Server on Google Cloud

You initialize the MCP Server connection using `McpToolset` with your HTTP endpoint. Pass it to your `LlmAgent` and the tools are live. You restrict access by filtering `tool_names` so the agent only sees what it needs. If you want a dedicated QA agent, you only expose `get_asset_details` and `add_comment`. The agent runs automated checks on Vertex AI and posts timestamped notes directly to the video file.

Map creative teams to enterprise directories

Video production gets messy when freelancers join the project. Your agent runs `list_collaborators` and `list_teams` to audit who has access to unreleased cuts. It matches those Frame.io user profiles from `get_my_profile` against your internal Google Workspace directories. If someone leaves the company, the agent flags their active sessions in `list_accounts`.

Setup guide

Set up Frame.io MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Frame.io tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Frame.io_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Frame.io tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install `google-adk` and create an `McpToolset` using your server URL. Pass this toolset into your `LlmAgent` constructor. The Gemini model immediately understands how to call the endpoints.

Yes. You pass a `tool_names` filter when setting up the `McpToolset`. This prevents the agent from calling `add_comment` if you only want it reading data via `list_assets`.

It does. You pull thousands of comments using `list_asset_comments` across multiple projects. Gemini processes the entire batch to identify recurring feedback trends.

The MCP Server connects via standard HTTP or Stdio transports. You configure this through the `StreamableHttpServerParameters` when building your integration.

The server reads strict metadata like file names, durations, and text comments. Vinkius enforces a zero-trust architecture, so your authentication tokens and BigQuery queries never bleed across isolated sessions.

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